The ACL 2013 Conference Handbook is already available and can

ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS

st

4 – 9 August | Sofia, Bulgaria

ConferenceHandbook

Useful Information

The 51st Annual Mee�ng of the Associa�on for Computa�onal Linguistics (ACL 2013)

August 4 (Sun) to August 9 (Fri), 2013National Palace of Cul�re, Sofia, Bulgaria

The Association for Computational LinguisticsThe Department of Computa�onal Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences

ACL 2013 is held under the aegis of the President of the Republic of Bulgaria Mr. Rosen Plevneliev

For the first �me, the annual mee�ng of the Associa�on for Computa�onal Linguistics (ACL) takes place in Bulgaria. ACL 2013 will be held in Sofia, Bulgaria's capital, August 4-9, 2013. As in previous years, the program of the conference in�udes a poster session, �torials, work�ops and demonstra�ons in addi�on to the main conference.

ACL is the premier conference of the field of computa�onal linguistics, covering a broad �e�rum of diverse resear� areas that are concerned with computa�onal approa�es to na�ral language. An exci�ng new development this year is that the conference program will in�ude the presenta�on of papers that have been accepted at Transa�ions of the ACL (TACL), the new journal of the ACL.

On behalf of the organizing commi�ee I invite you to join us in Sofia for ACL 2013!

Hinri� S�uetzeGeneral Chair

WELCOME TO ACL 2013!

h�p://acl2013.org

For the first time, the annual meeting of the Association for Computational Linguistics (ACL) takes place in Bulgaria. ACL 2013 will be held in Sofia, Bulgaria's capital, August 4-9, 2013. As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.

ACL is the premier conference of the field of computational linguistics, covering a broad spectrum of diverse research areas that are concerned with computational approaches to natural language. An exciting new development this year is that the conference program will include the presentation of papers that have been accepted at Transactions of the ACL (TACL), the new journal of the ACL.

On behalf of the organizing committee I invite you to join us in Sofia for ACL 2013!

Hinrich SchuetzeGeneral Chair

WELCOME TO ACL 2013!

Conference Committee

General ChairHinrich Schuetze, University of Munich

Program Co-ChairsPascale Fung, The Hong Kong University of Science and TechnologyMassimo Poesio, University of Essex

Local ChairSvetla Koeva, Bulgarian Academy of Sciences

Workshop Co-ChairsAoife Cahill, Educational Testing ServiceQun Liu, Dublin City University & Chinese Academy of Sciences

Tutorial Co-ChairsJohan Bos, University of GroningenKeith Hall, Google

Demo Co-ChairsMiriam Butt, University of KonstanzSarmad Hussain, Al-Khawarizmi Institute of Computer Science

Publication ChairsRoberto Navigli, Sapienza University of Rome (Chair)Jing-Shin Chang, National Chi Nan University (Co-Chair)

Faculty Advisors (Student Research Workshop)Steven Bethard, University of Colorado Boulder & KU LeuvenPreslav I. Nakov, Qatar Computing Research InstituteFeiyu Xu, DFKI, German Research Center for Artificial Intelligence

Student Chairs (Student Research Workshop)Anik Dey, The Hong Kong University of Science & TechnologyEva Vecchi, Università di TrentoSebastian Krause, German Research Center for Artificial IntelligenceIvelina Nikolova, Bulgarian Academy of Sciences

Mentoring ChairLeo Wanner, Universitat Pompeu Fabra

Publicity Co-ChairsAnisava Miltenova, Bulgarian Academy of SciencesIvan Derzhanski, Bulgarian Academy of SciencesAnna Korhonen, University of Cambridge

Business ManagerPriscilla Rasmussen, ACL

VenueThe National Palace of Culture, the largest convention centre in Bulgaria, prides itself on its unique architecture and great flexibility.

Located in the heart of Sofia and within walking distance of major hotels and tourist sites, it is the natural choice for an event of the scale of the ACL annual meeting.

The facilities include a conference hall seating 3600 and a number of customizable smaller halls and offices. The pedestrian plaza in front of the National Palace of Culture is a signature place for the Bulgarian capital.

51st ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS

Conference Committee

General ChairHinrich Schuetze, University of Munich

Program Co-ChairsPascale Fung, The Hong Kong University of Science and TechnologyMassimo Poesio, University of Essex

Local ChairSvetla Koeva, Bulgarian Academy of Sciences

Workshop Co-ChairsAoife Cahill, Educational Testing ServiceQun Liu, Dublin City University & Chinese Academy of Sciences

Tutorial Co-ChairsJohan Bos, University of GroningenKeith Hall, Google

Demo Co-ChairsMiriam Butt, University of KonstanzSarmad Hussain, Al-Khawarizmi Institute of Computer Science

Publication ChairsRoberto Navigli, Sapienza University of Rome (Chair)Jing-Shin Chang, National Chi Nan University (Co-Chair)

Faculty Advisors (Student Research Workshop)Steven Bethard, University of Colorado Boulder & KU LeuvenPreslav I. Nakov, Qatar Computing Research InstituteFeiyu Xu, DFKI, German Research Center for Artificial Intelligence

Student Chairs (Student Research Workshop)Anik Dey, The Hong Kong University of Science & TechnologyEva Vecchi, Università di TrentoSebastian Krause, German Research Center for Artificial IntelligenceIvelina Nikolova, Bulgarian Academy of Sciences

Mentoring ChairLeo Wanner, Universitat Pompeu Fabra

Publicity Co-ChairsAnisava Miltenova, Bulgarian Academy of SciencesIvan Derzhanski, Bulgarian Academy of SciencesAnna Korhonen, University of Cambridge

Business ManagerPriscilla Rasmussen, ACL

VenueThe National Palace of Culture, the largest convention centre in Bulgaria, prides itself on its unique architecture and great flexibility.

Located in the heart of Sofia and within walking distance of major hotels and tourist sites, it is the natural choice for an event of the scale of the ACL annual meeting.

The facilities include a conference hall seating 3600 and a number of customizable smaller halls and offices. The pedestrian plaza in front of the National Palace of Culture is a signature place for the Bulgarian capital.


Floor 0

Conference rooms situated on this floor – Hall 4, Hall 5, Hall 6

Main entrance

Hall 5Hall 4

Hall 6

4 5

Hall 1.4 Hall 1.5

Hall 1.2 Hall 1.7

Floor 1

Conference rooms situated on this floor – Halls 1.2, 1.4, 1.5, 1.7

Floor 0


Main entrance

Hall 5Hall 4

Hall 6

4 5

Hall 1.4 Hall 1.5

Hall 1.2 Hall 1.7

Floor 1

Conference rooms situated on this floor – Halls 1.2, 1.4, 1.5, 1.7

Floor 2

Poster sessions

POSTER SESSION AM – MultilingualityNLPCEE – NLP for Languages of Central and Eastern Europe and the BalkansNLPW – NLP for the Web and Social MediaSLP – Spoken Language ProcessingWS – Word Segmentation

POSTER SESSION BSA – Sentiment Analysis, Opinion Mining and Text ClassificationSMLM – Statistical and Machine Learning Methods in NLPTACL – Transactions of ACLTM – Text Mining and Information Extraction

POSTER SESSION ADCP – Discourse, Coreference and PragmaticsEM – Evaluation MethodsLSO – Lexical Semantics and OntologiesLRLP – Low Resource Language ProcessingNLPa – NLP ApplicationsTACL – Transactions of ACL

POSTER SESSION BS&P – Syntax and ParsingS – Semantics

Floor 3

Poster sessions

POSTER SESSION ACMP – Cognitive Modeling and PsycholinguisticsIR – Information RetrievalLR – Language ResourcesNLPc – NLP and Creativity

POSTER SESSION BQA – Question AnsweringS&G – Summarization & GenerationT&C – Tagging & Chunking

POSTER SESSION ADIS – Dialogue and Interactive SystemsMT:MAE – Machine Translation: Methods, Applications, Evaluation

POSTER SESSION BMT:SM – Machine Translation: Statistical Models

6 7

Floor 2

Poster sessions

POSTER SESSION AM – MultilingualityNLPCEE – NLP for Languages of Central and Eastern Europe and the BalkansNLPW – NLP for the Web and Social MediaSLP – Spoken Language ProcessingWS – Word Segmentation

POSTER SESSION BSA – Sentiment Analysis, Opinion Mining and Text ClassificationSMLM – Statistical and Machine Learning Methods in NLPTACL – Transactions of ACLTM – Text Mining and Information Extraction

POSTER SESSION ADCP – Discourse, Coreference and PragmaticsEM – Evaluation MethodsLSO – Lexical Semantics and OntologiesLRLP – Low Resource Language ProcessingNLPa – NLP ApplicationsTACL – Transactions of ACL

POSTER SESSION BS&P – Syntax and ParsingS – Semantics

Floor 3

Poster sessions

POSTER SESSION ACMP – Cognitive Modeling and PsycholinguisticsIR – Information RetrievalLR – Language ResourcesNLPc – NLP and Creativity

POSTER SESSION BQA – Question AnsweringS&G – Summarization & GenerationT&C – Tagging & Chunking

POSTER SESSION ADIS – Dialogue and Interactive SystemsMT:MAE – Machine Translation: Methods, Applications, Evaluation

POSTER SESSION BMT:SM – Machine Translation: Statistical Models

6 7

Floor 5


Hall 8Hall 7

Hall 9

Floor 7

Conference rooms situated on this floor – Hall 3

8 9

Hall 3

Floor 5


Hall 8Hall 7

Hall 9

Floor 7

Conference rooms situated on this floor – Hall 3

8 9

Hall 3

Floor 8

Conference rooms situated on this floor – Hall 3.1, Hall 3.2, Hall 10

Hall 3.2

Hall 10

Hall 3.1

thTutorials – Sun, August 4


Time Program Venue

8.00 – 18.00 Registration Floor 0

9.00 – 12.30 Morning Tutorials

Tutorial 1 Visual Features for Linguists: Basic image analysis techniques for multimodally-curious NLPers Hall 3.1

by Elia Bruni and Marco Baroni

Tutorial 2 Variational Inference for Structured NLP Models Hall 3.2

by David Burkett and Dan Klein

Tutorial 3 Decipherment Hall 4

by Kevin Knight

Tutorial 4 The mathematics of language learning Hall 1.5

by Andras Kornai, James Rogers, Gerald Penn and Anssi Yli-Jyrä

10.30 – 11.00 Coffee break Hall 9

12.30 – 14.00 Lunch break

14.00 – 17.30 Afternoon Tutorials

Tutorial 5 Exploiting Social Media for Natural Language Processing: Bridging the Gap between

Language-centric and Real-world Applications Hall 3.1

by Simone Paolo Ponzetto and Andrea Zielinski

Tutorial 6 Robust Automated Natural Language Processing with

Multiword Expressions and Collocations Hall 3.2

by Valia Kordoni and Markus Egg

Tutorial 7 Semantic Parsing with Combinatory Categorial Grammars Hall 4

by Yoav Artzi, Nicholas FitzGerald and Luke Zettlemoyer



15.30 – 16.00 Coffee break

18.30 – 21.00 Welcome Reception Sky Plaza

10 11

Floor 8

Conference rooms situated on this floor – Hall 3.1, Hall 3.2, Hall 10

Hall 3.2

Hall 10

Hall 3.1

thTutorials – Sun, August 4


Time Program Venue


9.00 – 12.30 Morning Tutorials

Tutorial 1 Visual Features for Linguists: Basic image analysis techniques for multimodally-curious NLPers Hall 3.1

by Elia Bruni and Marco Baroni

Tutorial 2 Variational Inference for Structured NLP Models Hall 3.2

by David Burkett and Dan Klein

Tutorial 3 Decipherment Hall 4

by Kevin Knight



10.30 – 11.00 Coffee break Hall 9


14.00 – 17.30 Afternoon Tutorials

Tutorial 5 Exploiting Social Media for Natural Language Processing: Bridging the Gap between

Language-centric and Real-world Applications Hall 3.1

by Simone Paolo Ponzetto and Andrea Zielinski

Tutorial 6 Robust Automated Natural Language Processing with

Multiword Expressions and Collocations Hall 3.2

by Valia Kordoni and Markus Egg

Tutorial 7 Semantic Parsing with Combinatory Categorial Grammars Hall 4

by Yoav Artzi, Nicholas FitzGerald and Luke Zettlemoyer




18.30 – 21.00 Welcome Reception Sky Plaza

10 11

VISUAL FEATURES FOR LINGUISTS: BASIC IMAGE ANALYSIS TECHNIQUES FOR MULTIMODALLY-CURIOUS NLPERSby Elia Bruni and Marco Baroni

thSunday, August 4 , 9.00 – 12.30 → Hall 3.1

Abstract

Features automatically extracted from images constitute a new and rich source of semantic knowledge that can complement information extracted from text. The convergence between vision- and text-based information can be exploited in scenarios where the two modalities must be combined to solve a target task (e.g., generating verbal descriptions of images, or finding the right images to illustrate a story). However, the potential applications for integrated visual features go beyond mixed-media scenarios. Because of their complementary nature with respect to language, visual features might provide perceptually grounded semantic information that can be exploited in purely linguistic domains.

The tutorial will first introduce basic techniques to encode image contents in terms of low-level features, such as the widely adopted SIFT descriptors. We will then show how these low-level descriptors are used to induce more abstract features, focusing on the well-established bags-of-visual-words method to represent images, but also briefly introducing more recent developments, that include capturing spatial information with pyramid representations, soft visual word clustering via Fisher encoding and attribute-based image representation. Next, we will discuss some example applications, andwe will conclude with a brief practical illustration of visual feature extraction using a software package we developed.

Presenters:

Elia BruniCenter for Mind/Brain Sciences, University of [email protected]

Marco BaroniCenter for Mind/Brain Sciences, University of [email protected]

Tutorial 1


VARIATIONAL INFERENCE FOR STRUCTURED NLP MODELSby David Burkett and Dan Klein


Abstract

Historically, key breakthroughs in structured NLP models, such as chain CRFs or PCFGs, have relied on imposing careful constraints on the locality of features in order to permit efficient dynamic programming for computing expectations or finding the highest-scoring structures. However, as modern structured models become more complex and seek to incorporate longer-range features, it is more and more often the case that performing exact inference is impossible (or at least impractical) and it is necessary to resort to some sort of approximation technique, such as beam search, pruning, or sampling. In the NLP community, one increasingly popular approach is the use of variational methods for computing approximate distributions.

The goal of the tutorial is to provide an introduction to variational methods for approximate inference, particularly mean field approximation and belief propagation. The intuition behind the mathematical derivation of variational methods is fairly simple: instead of trying to directly compute the distribution of interest, first consider some efficiently computable approximation of the original inference problem, then find the solution of the approximate inference problem that minimizes the distance to the true distribution. Though the full derivations can be some what tedious, the resulting procedures are quite straightforward, and typically consist of an iterative process of individually updating specific components of the model, conditioned on the rest. Although we will provide some theoretical background, the main goal of the tutorial is to provide a concrete procedural guide to using these approximate inference techniques, illustrated with detailed walkthroughs of examples from recent NLP literature.

Once both variational inference procedures have been described in detail, we'll provide a summary comparison of the two, along with some intuition about which approach is appropriate when. We'll also provide a guide to further exploration of the topic, briefly discussing other variational techniques, such as expectation propagation and convex relaxations, but concentrating mainly on providing pointers to additional resources for those who wish to learn more.

Presenters:

David BurkettComputer Science Division | Department of Electrical Engineering and Computer SciencesUniversity of California at [email protected]

Dan KleinComputer Science Division | Department of Electrical Engineering and Computer SciencesUniversity of California at [email protected]

Tutorial 2

12 13

VISUAL FEATURES FOR LINGUISTS: BASIC IMAGE ANALYSIS TECHNIQUES FOR MULTIMODALLY-CURIOUS NLPERSby Elia Bruni and Marco Baroni


Abstract

Features automatically extracted from images constitute a new and rich source of semantic knowledge that can complement information extracted from text. The convergence between vision- and text-based information can be exploited in scenarios where the two modalities must be combined to solve a target task (e.g., generating verbal descriptions of images, or finding the right images to illustrate a story). However, the potential applications for integrated visual features go beyond mixed-media scenarios. Because of their complementary nature with respect to language, visual features might provide perceptually grounded semantic information that can be exploited in purely linguistic domains.

The tutorial will first introduce basic techniques to encode image contents in terms of low-level features, such as the widely adopted SIFT descriptors. We will then show how these low-level descriptors are used to induce more abstract features, focusing on the well-established bags-of-visual-words method to represent images, but also briefly introducing more recent developments, that include capturing spatial information with pyramid representations, soft visual word clustering via Fisher encoding and attribute-based image representation. Next, we will discuss some example applications, andwe will conclude with a brief practical illustration of visual feature extraction using a software package we developed.

Presenters:

Elia BruniCenter for Mind/Brain Sciences, University of [email protected]

Marco BaroniCenter for Mind/Brain Sciences, University of [email protected]

Tutorial 1


VARIATIONAL INFERENCE FOR STRUCTURED NLP MODELSby David Burkett and Dan Klein


Abstract

Historically, key breakthroughs in structured NLP models, such as chain CRFs or PCFGs, have relied on imposing careful constraints on the locality of features in order to permit efficient dynamic programming for computing expectations or finding the highest-scoring structures. However, as modern structured models become more complex and seek to incorporate longer-range features, it is more and more often the case that performing exact inference is impossible (or at least impractical) and it is necessary to resort to some sort of approximation technique, such as beam search, pruning, or sampling. In the NLP community, one increasingly popular approach is the use of variational methods for computing approximate distributions.

The goal of the tutorial is to provide an introduction to variational methods for approximate inference, particularly mean field approximation and belief propagation. The intuition behind the mathematical derivation of variational methods is fairly simple: instead of trying to directly compute the distribution of interest, first consider some efficiently computable approximation of the original inference problem, then find the solution of the approximate inference problem that minimizes the distance to the true distribution. Though the full derivations can be some what tedious, the resulting procedures are quite straightforward, and typically consist of an iterative process of individually updating specific components of the model, conditioned on the rest. Although we will provide some theoretical background, the main goal of the tutorial is to provide a concrete procedural guide to using these approximate inference techniques, illustrated with detailed walkthroughs of examples from recent NLP literature.

Once both variational inference procedures have been described in detail, we'll provide a summary comparison of the two, along with some intuition about which approach is appropriate when. We'll also provide a guide to further exploration of the topic, briefly discussing other variational techniques, such as expectation propagation and convex relaxations, but concentrating mainly on providing pointers to additional resources for those who wish to learn more.

Presenters:

David BurkettComputer Science Division | Department of Electrical Engineering and Computer SciencesUniversity of California at [email protected]

Dan KleinComputer Science Division | Department of Electrical Engineering and Computer SciencesUniversity of California at [email protected]

Tutorial 2

12 13

DECIPHERMENTby Kevin Knight

thSunday, August 4 , 9.00 – 12.30 → Hall 4

Abstract

The first natural language processing systems had a straightforward goal: decipher coded messages sent by the enemy. Sixty years later, we have many more applications, including web search, question answering, summarization, speech recognition, and language translation. This tutorial explores connections between early decipherment research and today's NLP work. We find that many ideas from the earlier era have become core to the field, while others still remain to be picked up and developed.

We first cover classic military and diplomatic cipher types, including complex substitution ciphers implemented in the first electro-mechanical encryption machines. We look at mathematical tools (language recognition, frequency counting, smoothing) developed to decrypt such ciphers on proto-computers. We show algorithms and extensive empirical results for solving different types of ciphers, and we show the role of algorithms in recent decipherments of historical documents.

We then look at how foreign language can be viewed as a code for English, a concept developed by Alan Turing and Warren Weaver. We describe recently published work on building automatic translation systems from non-parallel data. We also demonstrate how some of the same algorithmic tools can be applied to natural language tasks like part-of-speech tagging and word alignment.

Turning back to historical ciphers, we explore a number of unsolved ciphers, giving results of initial computer experiments on several of them. Finally, we look briefly at writing as a way to encipher phoneme sequences, covering ancient scripts and modern applications.

Presenter:

Kevin KnightInformation Sciences Institute, University of Southern [email protected]

Tutorial 3


Over the past decade, attention has gradually shifted from the estimation of parameters to the learning of linguistic structure (for a survey see Smith 2011). The Mathematics of Language (MOL) SIG put together this tutorial, composed of three lectures, to highlight some alternative learning paradigms in speech, syntax, and semantics in the hopes of accelerating this trend.

Given the broad range of competing formal models such as templates in speech, PCFGs and various MCS models in syntax, logic-based and association-based models in semantics, it is somewhat surprising that the bulk of the applied work is still performed by HMMs. A particularly significant case in point is provided by PCFGs, which have not proved competitive with straight trigram models. Undergirding the practical failure of PCFGs is a more subtle theoretical problem, that the nonterminals in better PCFGs cannot be identified with the kind of nonterminal labels that grammarians assume, and conversely, PCFGs embodying some form of grammatical knowledge tend not to outperform flatly initialized models that make no use of such knowledge. A natural response to this outcome is to retrench and use less powerful formal models, and the first lecture will be spent in the subregular space of formal models even less powerful than finite state automata.

Compounding the enormous variety of formal models one may consider is the bewildering range of ML techniques one may bring to bear. In addition to the surprisingly useful classical techniques inherited from multivariate statistics such as Principal Component Analysis (PCA, Pearson 1901) and Linear Discriminant Analysis (LDA, Fisher 1936), computational linguists have experimented with a broad range of neural net, nearest neighbor, maxent, genetic/evolutionary, decision tree, max margin, boost, simulated annealing, and graphical model learners.

While many of these learners became standard in various domains of ML, within CL the basic HMM approach proved surprisingly resilient, and it is only very recently that deep learning techniques from neural computing are becoming competitive not just in speech, but also in OCR, paraphrase, sentiment analysis, parsing and vector-based semantic representations. The second lecture will provide a mathematical introduction to some of the fundamental techniques that lie beneath these linguistic applications of neural networks, such as: BFGS optimization, finite difference approximations of Hessians and Hessian-free optimization, contrastive divergence and variational inference.

In spite of the enormous progress brought by ML techniques, there remains a rather significant range of tasks where automated learners cannot yet get near human performance. One such is the unsupervised learning of word structure addressed by MorphoChallenge, another is the textual entailment task addressed by RTE. The third lecture recasts these and similar problems in terms of learning weighted edges in a sparse graph, and presents learning techniques that seem to have some potential to better find spare finite state and near-FS models than EM. We will provide a mathematical introduction to the Minimum Description Length (MDL) paradigm and spectral learning, and relate these to the better known L1 regularization technique and sparse overcomplete representations.

Presenters:

Andras KornaiBudapest Institute of Technology / Computer and Automation Research Institute, Hungarian Academy of [email protected], [email protected]

James RogersComputer Science Department, Earlham [email protected]

Gerald PennDepartment of Computer Science, University of Toronto / University of Trinity [email protected]

Anssi Yli-JyräDepartment of General Linguistics, University of [email protected]

THE MATHEMATICS OF LANGUAGE LEARNINGby Andras Kornai, James Rogers, Gerald Penn and Anssi Yli-Jyrä


Abstract

Tutorial 4

14 15

DECIPHERMENTby Kevin Knight


Abstract

The first natural language processing systems had a straightforward goal: decipher coded messages sent by the enemy. Sixty years later, we have many more applications, including web search, question answering, summarization, speech recognition, and language translation. This tutorial explores connections between early decipherment research and today's NLP work. We find that many ideas from the earlier era have become core to the field, while others still remain to be picked up and developed.

We first cover classic military and diplomatic cipher types, including complex substitution ciphers implemented in the first electro-mechanical encryption machines. We look at mathematical tools (language recognition, frequency counting, smoothing) developed to decrypt such ciphers on proto-computers. We show algorithms and extensive empirical results for solving different types of ciphers, and we show the role of algorithms in recent decipherments of historical documents.

We then look at how foreign language can be viewed as a code for English, a concept developed by Alan Turing and Warren Weaver. We describe recently published work on building automatic translation systems from non-parallel data. We also demonstrate how some of the same algorithmic tools can be applied to natural language tasks like part-of-speech tagging and word alignment.

Turning back to historical ciphers, we explore a number of unsolved ciphers, giving results of initial computer experiments on several of them. Finally, we look briefly at writing as a way to encipher phoneme sequences, covering ancient scripts and modern applications.

Presenter:

Kevin KnightInformation Sciences Institute, University of Southern [email protected]

Tutorial 3


Over the past decade, attention has gradually shifted from the estimation of parameters to the learning of linguistic structure (for a survey see Smith 2011). The Mathematics of Language (MOL) SIG put together this tutorial, composed of three lectures, to highlight some alternative learning paradigms in speech, syntax, and semantics in the hopes of accelerating this trend.

Given the broad range of competing formal models such as templates in speech, PCFGs and various MCS models in syntax, logic-based and association-based models in semantics, it is somewhat surprising that the bulk of the applied work is still performed by HMMs. A particularly significant case in point is provided by PCFGs, which have not proved competitive with straight trigram models. Undergirding the practical failure of PCFGs is a more subtle theoretical problem, that the nonterminals in better PCFGs cannot be identified with the kind of nonterminal labels that grammarians assume, and conversely, PCFGs embodying some form of grammatical knowledge tend not to outperform flatly initialized models that make no use of such knowledge. A natural response to this outcome is to retrench and use less powerful formal models, and the first lecture will be spent in the subregular space of formal models even less powerful than finite state automata.

Compounding the enormous variety of formal models one may consider is the bewildering range of ML techniques one may bring to bear. In addition to the surprisingly useful classical techniques inherited from multivariate statistics such as Principal Component Analysis (PCA, Pearson 1901) and Linear Discriminant Analysis (LDA, Fisher 1936), computational linguists have experimented with a broad range of neural net, nearest neighbor, maxent, genetic/evolutionary, decision tree, max margin, boost, simulated annealing, and graphical model learners.

While many of these learners became standard in various domains of ML, within CL the basic HMM approach proved surprisingly resilient, and it is only very recently that deep learning techniques from neural computing are becoming competitive not just in speech, but also in OCR, paraphrase, sentiment analysis, parsing and vector-based semantic representations. The second lecture will provide a mathematical introduction to some of the fundamental techniques that lie beneath these linguistic applications of neural networks, such as: BFGS optimization, finite difference approximations of Hessians and Hessian-free optimization, contrastive divergence and variational inference.

In spite of the enormous progress brought by ML techniques, there remains a rather significant range of tasks where automated learners cannot yet get near human performance. One such is the unsupervised learning of word structure addressed by MorphoChallenge, another is the textual entailment task addressed by RTE. The third lecture recasts these and similar problems in terms of learning weighted edges in a sparse graph, and presents learning techniques that seem to have some potential to better find spare finite state and near-FS models than EM. We will provide a mathematical introduction to the Minimum Description Length (MDL) paradigm and spectral learning, and relate these to the better known L1 regularization technique and sparse overcomplete representations.

Presenters:

Andras KornaiBudapest Institute of Technology / Computer and Automation Research Institute, Hungarian Academy of [email protected], [email protected]

James RogersComputer Science Department, Earlham [email protected]

Gerald PennDepartment of Computer Science, University of Toronto / University of Trinity [email protected]

Anssi Yli-JyräDepartment of General Linguistics, University of [email protected]

THE MATHEMATICS OF LANGUAGE LEARNINGby Andras Kornai, James Rogers, Gerald Penn and Anssi Yli-Jyrä


Abstract

Tutorial 4

14 15

EXPLOITING SOCIAL MEDIA FOR NATURAL LANGUAGE PROCESSING: BRIDGING THE GAP BETWEEN LANGUAGE-CENTRIC AND REAL-WORLD APPLICATIONSby Simone Paolo Ponzetto and Andrea Zielinski


Abstract

Social media like Twitter and micro-blogs provide a goldmine of text, shallow markup annotations and network structure. These information sources can all be exploited together in order to automatically acquire vast amounts of up-to-date, wide-coverage structured knowledge. This knowledge, in turn, can be used to measure the pulse of a variety of social phenomena like political events, activism and stock prices, as well as to detect emerging events such as natural disasters (earthquakes, tsunami, etc.).

The main purpose of this tutorial is to introduce social media as a resource to the Natural Language Processing (NLP) community both from a scientific and an application-oriented perspective. To this end, we focus on micro-blogs such as Twitter, and show how it can be successfully mined to perform complex NLP tasks such as the identification of events, topics and trends. Furthermore, this information can be used to build high-end socially intelligent applications that tap the wisdom of the crowd on a large scale, thus successfully bridging the gap between computational text analysis and real-world, mission-critical applications such as financial forecasting and natural crisis management.

Presenters:

Simone Paolo PonzettoResearch Group of Data and Web Science, Universität [email protected]

Andrea ZielinskiFraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (IOSB)[email protected]

Tutorial 5


16

ROBUST AUTOMATED NATURAL LANGUAGE PROCESSING WITH MULTIWORD EXPRESSIONS AND COLLOCATIONSby Valia Kordoni and Markus Egg


Abstract

Multi Word Expressions (MWEs) are a key issue and a current weakness for NLP tasks that need some degree of semantic interpretation, with potential contributions to natural language parsing and generation, as well as applications such as machine translation, information retrieval and information extraction. Therefore, a tutorial on this topic is of great relevance for researchers in NLP and related areas.

Attendees to this tutorial should gain insight into linguistic and distributional characteristics of MWEs and, most importantly, their relevance for robust automated natural language processing and language technology, with a thorough overview of methods and resources that support their use. We will provide a theoretical and practical introduction to the topic, with demonstrations of resources and tools available, aiming to equip the attendees with some starting recipes for MWE processing, including tools for the identification and resource construction (e.g. NSP, UCS, mwetoolkit) and annotation (e.g. jMWE). Our target audience includes researchers and practitioners in Language Technology (not necessarily experts in MWEs) who are interested in tasks that involve or could benefit from considering MWEs as a pervasive phenomenon in human language and communication.

Presenters:

Valia KordoniDepartment of English and American Studies, Humboldt University Berlin [email protected]

Markus EggDepartment of English and American Studies, Humboldt University Berlin [email protected]

Tutorial 6

17

EXPLOITING SOCIAL MEDIA FOR NATURAL LANGUAGE PROCESSING: BRIDGING THE GAP BETWEEN LANGUAGE-CENTRIC AND REAL-WORLD APPLICATIONSby Simone Paolo Ponzetto and Andrea Zielinski


Abstract

Social media like Twitter and micro-blogs provide a goldmine of text, shallow markup annotations and network structure. These information sources can all be exploited together in order to automatically acquire vast amounts of up-to-date, wide-coverage structured knowledge. This knowledge, in turn, can be used to measure the pulse of a variety of social phenomena like political events, activism and stock prices, as well as to detect emerging events such as natural disasters (earthquakes, tsunami, etc.).

The main purpose of this tutorial is to introduce social media as a resource to the Natural Language Processing (NLP) community both from a scientific and an application-oriented perspective. To this end, we focus on micro-blogs such as Twitter, and show how it can be successfully mined to perform complex NLP tasks such as the identification of events, topics and trends. Furthermore, this information can be used to build high-end socially intelligent applications that tap the wisdom of the crowd on a large scale, thus successfully bridging the gap between computational text analysis and real-world, mission-critical applications such as financial forecasting and natural crisis management.

Presenters:

Simone Paolo PonzettoResearch Group of Data and Web Science, Universität [email protected]

Andrea ZielinskiFraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (IOSB)[email protected]

Tutorial 5


16

ROBUST AUTOMATED NATURAL LANGUAGE PROCESSING WITH MULTIWORD EXPRESSIONS AND COLLOCATIONSby Valia Kordoni and Markus Egg


Abstract

Multi Word Expressions (MWEs) are a key issue and a current weakness for NLP tasks that need some degree of semantic interpretation, with potential contributions to natural language parsing and generation, as well as applications such as machine translation, information retrieval and information extraction. Therefore, a tutorial on this topic is of great relevance for researchers in NLP and related areas.

Attendees to this tutorial should gain insight into linguistic and distributional characteristics of MWEs and, most importantly, their relevance for robust automated natural language processing and language technology, with a thorough overview of methods and resources that support their use. We will provide a theoretical and practical introduction to the topic, with demonstrations of resources and tools available, aiming to equip the attendees with some starting recipes for MWE processing, including tools for the identification and resource construction (e.g. NSP, UCS, mwetoolkit) and annotation (e.g. jMWE). Our target audience includes researchers and practitioners in Language Technology (not necessarily experts in MWEs) who are interested in tasks that involve or could benefit from considering MWEs as a pervasive phenomenon in human language and communication.

Presenters:

Valia KordoniDepartment of English and American Studies, Humboldt University Berlin [email protected]

Markus EggDepartment of English and American Studies, Humboldt University Berlin [email protected]

Tutorial 6

17

SEMANTIC PARSING WITH COMBINATORY CATEGORIAL GRAMMARSby Yoav Artzi, Nicholas FitzGerald and Luke Zettlemoyer


Abstract

Semantic parsers map natural language sentences to formal representations of their underlying meaning. Building accurate semantic parsers without prohibitive engineering costs is a long-standing, open research problem.

The tutorial will describe general principles for building semantic parsers. The presentation will be divided into two main parts: modeling and learning. The modeling section will include best practices for grammar design and choice of semantic representation. The discussion will be guided by examples from several domains. To illustrate the choices to be made and show how they can be approached within a real-life representation language, we will use lambda-calculus meaning representations. In the learning part, we will describe a unified approach for learning Combinatory Categorial Grammar (CCG) semantic parsers, that induces both a CCG lexicon and the parameters of a parsing model. The approach learns from data with labeled meaning representations, as well as from more easily gathered weak supervision. It also enables grounded learning where the semantic parser is used in an interactive environment, for example to read and execute instructions.

The ideas we will discuss are widely applicable. The semantic modeling approach, while implemented in lambda-calculus, could be applied to manyother formal languages. Similarly, the algorithms for inducing CCGs focus on tasks that are formalism independent, learning the meaning of words and estimating parsing parameters. No prior knowledge of CCGs is required. The tutorial will be backed by implementation and experiments in the University of Washington Semantic Parsing Framework (UW SPF -http://yoavartzi.com/spf).

Presenters:

Yoav ArtziDepartment of Computer Science & Engineering, University of [email protected]

Nicholas FitzGeraldDepartment of Computer Science & Engineering, University of [email protected]

Luke ZettlemoyerDepartment of Computer Science & Engineering, University of [email protected]

Tutorial 7

18


MAINCONFERENCEPROGRAM

SEMANTIC PARSING WITH COMBINATORY CATEGORIAL GRAMMARSby Yoav Artzi, Nicholas FitzGerald and Luke Zettlemoyer


Abstract

Semantic parsers map natural language sentences to formal representations of their underlying meaning. Building accurate semantic parsers without prohibitive engineering costs is a long-standing, open research problem.

The tutorial will describe general principles for building semantic parsers. The presentation will be divided into two main parts: modeling and learning. The modeling section will include best practices for grammar design and choice of semantic representation. The discussion will be guided by examples from several domains. To illustrate the choices to be made and show how they can be approached within a real-life representation language, we will use lambda-calculus meaning representations. In the learning part, we will describe a unified approach for learning Combinatory Categorial Grammar (CCG) semantic parsers, that induces both a CCG lexicon and the parameters of a parsing model. The approach learns from data with labeled meaning representations, as well as from more easily gathered weak supervision. It also enables grounded learning where the semantic parser is used in an interactive environment, for example to read and execute instructions.

The ideas we will discuss are widely applicable. The semantic modeling approach, while implemented in lambda-calculus, could be applied to manyother formal languages. Similarly, the algorithms for inducing CCGs focus on tasks that are formalism independent, learning the meaning of words and estimating parsing parameters. No prior knowledge of CCGs is required. The tutorial will be backed by implementation and experiments in the University of Washington Semantic Parsing Framework (UW SPF -http://yoavartzi.com/spf).

Presenters:

Yoav ArtziDepartment of Computer Science & Engineering, University of [email protected]

Nicholas FitzGeraldDepartment of Computer Science & Engineering, University of [email protected]

Luke ZettlemoyerDepartment of Computer Science & Engineering, University of [email protected]

Tutorial 7

18


MAINCONFERENCEPROGRAM



9.00 – 9.30 Opening Session Hall 3

9.30 – 10.30 Invited Talk: Harald Baayen Hall 3

th10.30 – 11.00 Coffee Break 5 Floor

11.00 – 12.15 Parallel Sessions Halls 3, 6, 7, 8, 10

12.15 – 13.45 Lunch Break 12.15 – 13.45 Student Lunch Continental Plaza





nd rd18.30 – 21.00 Poster Session + System Demonstrations + 2 and 3 Floors Student Research Workshop + Poster Dinner

Invited Talk: Harald Baayen (Tuebingen/Alberta)When Parsing Makes Things Worse: An Eye-tracking Study of English Compounds

thMonday, August 5 , 2013, 9.30 am – 10.30 am Hall 3→Short Bio: Prof. Dr. Rolf Harald Baayen is regarded as one of the best and most innovative researchers in the field of vocabulary research and quantitative linguistics. He is a pioneer of computer-assisted and empirical linguistic research and psycholinguistics, and has made fundamental contributions to the understanding of human speech and the role of the memory in language processing. Prof. Harald Baayen was born in the USA in 1958. He got a PhD in 1989 and was a postdoctoral researcher at Vrije Universiteit Amsterdam. He worked at the Max Planck Institute for Psycholinguistics in Nijmegen, the Netherlands (1990 –�1998), and at Radboud Universiteit Nijmegen, initially as an associate and subsequently as a full professor in Quantitative Linguistics (2006). Since 2007, he has been professor at the Department of Linguistics, University of Alberta, Edmonton, Canada. His honors include the PIONEER Award of the Netherlands Organization for Scientific Research in 1998, and the Alexander von Humboldt Professorship 2012.

th Main Conference: Mon, August 5

Overview

20


Time Activity Hall 3 Hall 6 Hall 7 Hall 8 Hall 10 Other



9.30 Invited Talk 1:

Harald Baayen Hall 3

10.30 Coffee Break

11.00 Papers LP 1a LP 1b LP 1c LP 1d LP 1e

Machine Statistical & Semantics I Discourse, Syntax &

Translation: Machine Learning Coreference & Parsing I

Statistical Methods in NLP I Pragmatics I

Models I

12.15 Lunch Break


Machine Statistical & Semantics II Discourse, Syntax &

Translation: Machine Learning Coreference & Parsing II

Statistical Methods in NLP II Pragmatics II

Models II


Machine Statistical & Semantics III Low Resource Syntax &

Translation: Machine Learning Language Parsing III

Statistical Methods in NLP III Processing

Models III NLP

Applications

16.15 Coffee Break

16.45 Papers SP 4a SP 4b SP 4c SP 4d SP 4e

Machine NLP Applications Semantics Discourse, Syntax &

Translation: Coreference & Parsing

Statistical Pragmatics

Models

18.30 Poster Session + 2nd & 3rd

System Floor s

Demonstrations +

Buffet

21.00 End

thProgram – Mon, August 5

21




9.30 – 10.30 Invited Talk: Harald Baayen Hall 3



12.15 – 13.45 Lunch Break 12.15 – 13.45 Student Lunch Continental Plaza





nd rd18.30 – 21.00 Poster Session + System Demonstrations + 2 and 3 Floors Student Research Workshop + Poster Dinner

Invited Talk: Harald Baayen (Tuebingen/Alberta)When Parsing Makes Things Worse: An Eye-tracking Study of English Compounds

thMonday, August 5 , 2013, 9.30 am – 10.30 am Hall 3→Short Bio: Prof. Dr. Rolf Harald Baayen is regarded as one of the best and most innovative researchers in the field of vocabulary research and quantitative linguistics. He is a pioneer of computer-assisted and empirical linguistic research and psycholinguistics, and has made fundamental contributions to the understanding of human speech and the role of the memory in language processing. Prof. Harald Baayen was born in the USA in 1958. He got a PhD in 1989 and was a postdoctoral researcher at Vrije Universiteit Amsterdam. He worked at the Max Planck Institute for Psycholinguistics in Nijmegen, the Netherlands (1990 –�1998), and at Radboud Universiteit Nijmegen, initially as an associate and subsequently as a full professor in Quantitative Linguistics (2006). Since 2007, he has been professor at the Department of Linguistics, University of Alberta, Edmonton, Canada. His honors include the PIONEER Award of the Netherlands Organization for Scientific Research in 1998, and the Alexander von Humboldt Professorship 2012.

th Main Conference: Mon, August 5

Overview

20





9.30 Invited Talk 1:

Harald Baayen Hall 3

10.30 Coffee Break


Machine Statistical & Semantics I Discourse, Syntax &

Translation: Machine Learning Coreference & Parsing I

Statistical Methods in NLP I Pragmatics I

Models I

12.15 Lunch Break


Machine Statistical & Semantics II Discourse, Syntax &

Translation: Machine Learning Coreference & Parsing II

Statistical Methods in NLP II Pragmatics II

Models II


Machine Statistical & Semantics III Low Resource Syntax &

Translation: Machine Learning Language Parsing III

Statistical Methods in NLP III Processing

Models III NLP

Applications

16.15 Coffee Break

16.45 Papers SP 4a SP 4b SP 4c SP 4d SP 4e

Machine NLP Applications Semantics Discourse, Syntax &

Translation: Coreference & Parsing

Statistical Pragmatics

Models

18.30 Poster Session + 2nd & 3rd

System Floor s

Demonstrations +

Buffet

21.00 End

thProgram – Mon, August 5

21

8.00 – 18.00 Registration Floor 0→

9.00 – 9.30 Opening Session Hall 3→

9.30 Invited Talk: Harald Baayen (Tuebingen/Alberta) When Parsing Makes Things Worse: An Eye-tracking Study of English Compounds Hall 3→

th10.30 Coffee Break 5 Floor→

LONG PAPERS, SHORT PAPERS, POSTERS, SYSTEM DEMONSTRATIONS, STUDENT RESEARCH WORKSHOP, TACL

Oral Presentations → Halls 3, 6, 7, 8, 10

LONG PAPERS

LP 1a Machine Translation: Statistical Models I → Hall 3

11.00 A Shift-Reduce Parsing Algorithm for Phrase-based String-to-Dependency Translation Yang Liu

11.25 Integrating Translation Memory into Phrase-based Machine Translation during Decoding Kun Wang, Chengqing Zong and Keh-Yih Su 11.50 Training Nondeficient Variants of IBM-3 and IBM-4 for Word Alignment Thomas Schoenemann LP 1b Statistical and Machine Learning Methods in NLP I → Hall 6 11.00 Modelling Annotator Bias with Multi-task Gaussian Processes: An Application to Machine Translation Quality Estimation Trevor Cohn and Lucia Specia 11.25 Smoothed Marginal Distribution Constraints for Language Modeling Brian Roark, Cyril Allauzen and Michael Riley 11.50 Grounded Language Learning from Videos Described with Sentences Haonan Yu and Jeffrey Mark Siskind

LP 1c Semantics I → Hall 7

11.00 Plurality, Negation, and Quantification:Towards Comprehensive Quantifier Scope Disambiguation Mehdi Manshadi and James Allen

thExtended Daily Program – Mon, August 5


22

11.25 Joint Event Extraction via Structured Prediction with Global Features Qi Li, Heng Ji and Liang Huang

11.50 Language-Independent Discriminative Parsing of Temporal Expressions Gabor Angeli and Jakob Uszkoreit

LP 1d Discourse, Coreference and Pragmatics I → Hall 8

11.00 Graph-based Local Coherence Modeling Camille Guinaudeau and Michael Strube

11.25 Recognizing Rare Social Phenomena in Conversation: Empowerment Detection in Support Group Chatrooms Elijah Mayfield, David Adamson and Carolyn Penstein Rosé

11.50 Decentralized Entity-Level Modeling for Coreference Resolution Greg Durrett, David Hall and Dan Klein

LP 1e Syntax and Parsing I → Hall 10 11.00 Chinese Parsing Exploiting Characters Meishan Zhang, Yue Zhang, Wanxiang Che and Ting Liu

11.25 A Transition-based Dependency Parser Using a Dynamic Parsing Strategy Francesco Sartorio, Giorgio Satta and Joakim Nivre

11.50 General binarization for parsing and translation Matthias Büchse, Alexander Koller and Heiko Vogler 12.15 Lunch Break12.15 Student Lunch

LP 2a Machine Translation: Statistical Models II → Hall 3

13.45 Distortion Model Considering Rich Context for Statistical Machine Translation Isao Goto, Masao Utiyama, Eiichiro Sumita, Akihiro Tamura and Sadao Kurohashi

14.10 Word Alignment Modeling with Context Dependent Deep Neural Network Nan Yang, Shujie Liu, Mu Li, Ming Zhou and Nenghai Yu

14.35 Microblogs as Parallel Corpora Wang Ling, Guang Xiang, Chris Dyer, Alan Black and Isabel Trancoso

LP 2b Statistical and Machine Learning Methods in NLP II → Hall 6

13.45 Improved Bayesian Logistic Supervised Topic Models with Data Augmentation Jun Zhu, Xun Zheng and Bo Zhang

23


9.00 – 9.30 Opening Session Hall 3→

9.30 Invited Talk: Harald Baayen (Tuebingen/Alberta) When Parsing Makes Things Worse: An Eye-tracking Study of English Compounds Hall 3→


LONG PAPERS, SHORT PAPERS, POSTERS, SYSTEM DEMONSTRATIONS, STUDENT RESEARCH WORKSHOP, TACL


LONG PAPERS

LP 1a Machine Translation: Statistical Models I → Hall 3

11.00 A Shift-Reduce Parsing Algorithm for Phrase-based String-to-Dependency Translation Yang Liu

11.25 Integrating Translation Memory into Phrase-based Machine Translation during Decoding Kun Wang, Chengqing Zong and Keh-Yih Su 11.50 Training Nondeficient Variants of IBM-3 and IBM-4 for Word Alignment Thomas Schoenemann LP 1b Statistical and Machine Learning Methods in NLP I → Hall 6 11.00 Modelling Annotator Bias with Multi-task Gaussian Processes: An Application to Machine Translation Quality Estimation Trevor Cohn and Lucia Specia 11.25 Smoothed Marginal Distribution Constraints for Language Modeling Brian Roark, Cyril Allauzen and Michael Riley 11.50 Grounded Language Learning from Videos Described with Sentences Haonan Yu and Jeffrey Mark Siskind

LP 1c Semantics I → Hall 7

11.00 Plurality, Negation, and Quantification:Towards Comprehensive Quantifier Scope Disambiguation Mehdi Manshadi and James Allen

thExtended Daily Program – Mon, August 5


22

11.25 Joint Event Extraction via Structured Prediction with Global Features Qi Li, Heng Ji and Liang Huang

11.50 Language-Independent Discriminative Parsing of Temporal Expressions Gabor Angeli and Jakob Uszkoreit

LP 1d Discourse, Coreference and Pragmatics I → Hall 8

11.00 Graph-based Local Coherence Modeling Camille Guinaudeau and Michael Strube

11.25 Recognizing Rare Social Phenomena in Conversation: Empowerment Detection in Support Group Chatrooms Elijah Mayfield, David Adamson and Carolyn Penstein Rosé

11.50 Decentralized Entity-Level Modeling for Coreference Resolution Greg Durrett, David Hall and Dan Klein

LP 1e Syntax and Parsing I → Hall 10 11.00 Chinese Parsing Exploiting Characters Meishan Zhang, Yue Zhang, Wanxiang Che and Ting Liu

11.25 A Transition-based Dependency Parser Using a Dynamic Parsing Strategy Francesco Sartorio, Giorgio Satta and Joakim Nivre

11.50 General binarization for parsing and translation Matthias Büchse, Alexander Koller and Heiko Vogler 12.15 Lunch Break12.15 Student Lunch

LP 2a Machine Translation: Statistical Models II → Hall 3

13.45 Distortion Model Considering Rich Context for Statistical Machine Translation Isao Goto, Masao Utiyama, Eiichiro Sumita, Akihiro Tamura and Sadao Kurohashi

14.10 Word Alignment Modeling with Context Dependent Deep Neural Network Nan Yang, Shujie Liu, Mu Li, Ming Zhou and Nenghai Yu

14.35 Microblogs as Parallel Corpora Wang Ling, Guang Xiang, Chris Dyer, Alan Black and Isabel Trancoso

LP 2b Statistical and Machine Learning Methods in NLP II → Hall 6

13.45 Improved Bayesian Logistic Supervised Topic Models with Data Augmentation Jun Zhu, Xun Zheng and Bo Zhang

23

14.10 Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning Miguel Almeida and Andre Martins

14.35 Unsupervised Transcription of Historical Documents Taylor Berg-Kirkpatrick, Greg Durrett and Dan Klein

LP 2c Semantics II → Hall 7

13.45 Adapting Discriminative Reranking to Grounded Language Learning Joohyun Kim and Raymond Mooney

14.10 Universal Conceptual Cognitive Annotation (UCCA) Omri Abend and Ari Rappoport

14.35 Linking Tweets to News: A Framework to Enrich Short Text Data in Social Media Weiwei Guo, Hao Li, Heng Ji and Mona Diab

LP 2d Discourse, Coreference and Pragmatics II → Hall 8

13.45 A Computational Approach to Politeness with Application to Social Factors Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec and Christopher Potts

14.10 Modeling Thesis Clarity in Student Essays Isaac Persing and Vincent Ng

14.35 Translating Italian Connectives into Italian Sign Language Camillo Lugaresi and Barbara Di Eugenio LP 2e Syntax and Parsing II → Hall 10 13.45 Stop-probability Estimates Computed on a Large Corpus Improve Unsupervised Dependency Parsing David Marecek and Milan Straka

14.10 Transfer Learning for Constituency-based Grammars Yuan Zhang, Regina Barzilay and Amir Globerson

14.35 A Context Free TAG Variant Ben Swanson, Elif Yamangil, Stuart Shieber and Eugene Charniak

LP 3a Machine Translation: Statistical Models III → Hall 3 15.00 Fast and Adaptive Online Training of Feature-Rich Translation Models Spence Green, Sida Wang, Daniel Cer and Christopher D. Manning

15.25 Advancements in Reordering Models for Statistical Machine Translation Minwei Feng, Jan-Thorsten Peter and Hermann Ney

THEXTENDED DAILY PROGRAM – MON, AUGUST 5

24

15.50 A Markov Model of Machine Translation using Non-parametric Bayesian Inference Yang Feng and Trevor Cohn

LP 3b Statistical and Machine Learning Methods in NLP III → Hall 6 15.00 Scaling Semi-supervised Naive Bayes with Feature Marginals Michael Lucas and Doug Downey

15.25 Learning Latent Personas of Film Characters David Bamman, Brendan O'Connor and Noah A. Smith

15.50 Scalable Decipherment for Machine Translation via Hash Sampling Sujith Ravi

LP 3c Semantics III → Hall 7 15.00 Automatic Interpretation of the English Possessive Stephen Tratz and Eduard Hovy

15.25 Is a 204 cm Man Tall or Small ? Acquisition of Numerical Common Sense from the Web Katsuma Narisawa, Yotaro Watanabe, Junta Mizuno, Naoaki Okazaki and Kentaro Inui

15.50 Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors Jackie Chi Kit Cheung and Gerald Penn

LP 3d Low Resource Language Processing NLP Applications → Hall 8

15.00 Extracting Bilingual Terminologies from Comparable Corpora Ahmet Aker, Monica Paramita and Rob Gaizauskas

15.25 The Haves and the Have-Nots: Leveraging Unlabelled Corpora for Sentiment Analysis Kashyap Popat, Balamurali A.R, Pushpak Bhattacharyya and Gholamreza Haffari

15.50 Large-scale Semantic Parsing via Schema Matching and Lexicon Extension Qingqing Cai and Alexander Yates

LP 3e Syntax and Parsing III → Hall 10 15.00 Fast and Accurate Shift-Reduce Constituent Parsing Muhua Zhu, Yue Zhang, Wenliang Chen, Min Zhang and Jingbo Zhu

15.25 Nonconvex Global Optimization for Latent-Variable Models Matthew Gormley and Jason Eisner

15.50 Parsing with Compositional Vector Grammars Richard Socher, John Bauer, Christopher Manning and Andrew Ng 16.15 Coffee Break

25

14.10 Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning Miguel Almeida and Andre Martins

14.35 Unsupervised Transcription of Historical Documents Taylor Berg-Kirkpatrick, Greg Durrett and Dan Klein

LP 2c Semantics II → Hall 7

13.45 Adapting Discriminative Reranking to Grounded Language Learning Joohyun Kim and Raymond Mooney

14.10 Universal Conceptual Cognitive Annotation (UCCA) Omri Abend and Ari Rappoport

14.35 Linking Tweets to News: A Framework to Enrich Short Text Data in Social Media Weiwei Guo, Hao Li, Heng Ji and Mona Diab

LP 2d Discourse, Coreference and Pragmatics II → Hall 8

13.45 A Computational Approach to Politeness with Application to Social Factors Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec and Christopher Potts

14.10 Modeling Thesis Clarity in Student Essays Isaac Persing and Vincent Ng

14.35 Translating Italian Connectives into Italian Sign Language Camillo Lugaresi and Barbara Di Eugenio LP 2e Syntax and Parsing II → Hall 10 13.45 Stop-probability Estimates Computed on a Large Corpus Improve Unsupervised Dependency Parsing David Marecek and Milan Straka

14.10 Transfer Learning for Constituency-based Grammars Yuan Zhang, Regina Barzilay and Amir Globerson

14.35 A Context Free TAG Variant Ben Swanson, Elif Yamangil, Stuart Shieber and Eugene Charniak

LP 3a Machine Translation: Statistical Models III → Hall 3 15.00 Fast and Adaptive Online Training of Feature-Rich Translation Models Spence Green, Sida Wang, Daniel Cer and Christopher D. Manning

15.25 Advancements in Reordering Models for Statistical Machine Translation Minwei Feng, Jan-Thorsten Peter and Hermann Ney


24

15.50 A Markov Model of Machine Translation using Non-parametric Bayesian Inference Yang Feng and Trevor Cohn

LP 3b Statistical and Machine Learning Methods in NLP III → Hall 6 15.00 Scaling Semi-supervised Naive Bayes with Feature Marginals Michael Lucas and Doug Downey

15.25 Learning Latent Personas of Film Characters David Bamman, Brendan O'Connor and Noah A. Smith

15.50 Scalable Decipherment for Machine Translation via Hash Sampling Sujith Ravi

LP 3c Semantics III → Hall 7 15.00 Automatic Interpretation of the English Possessive Stephen Tratz and Eduard Hovy

15.25 Is a 204 cm Man Tall or Small ? Acquisition of Numerical Common Sense from the Web Katsuma Narisawa, Yotaro Watanabe, Junta Mizuno, Naoaki Okazaki and Kentaro Inui

15.50 Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors Jackie Chi Kit Cheung and Gerald Penn

LP 3d Low Resource Language Processing NLP Applications → Hall 8

15.00 Extracting Bilingual Terminologies from Comparable Corpora Ahmet Aker, Monica Paramita and Rob Gaizauskas

15.25 The Haves and the Have-Nots: Leveraging Unlabelled Corpora for Sentiment Analysis Kashyap Popat, Balamurali A.R, Pushpak Bhattacharyya and Gholamreza Haffari

15.50 Large-scale Semantic Parsing via Schema Matching and Lexicon Extension Qingqing Cai and Alexander Yates

LP 3e Syntax and Parsing III → Hall 10 15.00 Fast and Accurate Shift-Reduce Constituent Parsing Muhua Zhu, Yue Zhang, Wenliang Chen, Min Zhang and Jingbo Zhu

15.25 Nonconvex Global Optimization for Latent-Variable Models Matthew Gormley and Jason Eisner

15.50 Parsing with Compositional Vector Grammars Richard Socher, John Bauer, Christopher Manning and Andrew Ng 16.15 Coffee Break

25

SHORT PAPERS

SP 4a Machine Translation: Statistical Models → Hall 3

16.45 Translating Dialectal Arabic to English Hassan Sajjad, Kareem Darwish and Yonatan Belinkov

17.05 Exact Maximum Inference for the Fertility Hidden Markov Model Chris Quirk

17.25 A Tale about PRO and Monsters Preslav Nakov, Francisco Guzman and Stephan Vogel

17.45 Supervised Model Learning with Feature Grouping based on a Discrete Constraint Jun Suzuki and Masaaki Nagata

SP 4b NLP Applications → Hall 6

16.45 Exploiting Topic-based Twitter Sentiment for Stock Prediction Jianfeng Si, Arjun Mukherjee, Bing Liu, Qing Li, Huayi Li and xiaotie Deng

17.05 Learning Entity Representation for Entity Disambiguation Zhengyan He, Shujie Liu, Mu Li, Ming Zhou, Houfeng Wang and Longkai Zhang

17.25 Natural Language Models for Predicting Programming Comments Dana Movshovitz-Attias and William Cohen

17.45 Paraphrasing Adaptation for Web Search Ranking Chenguang Wang, Nan Duan, Ming Zhou and Ming Zhang

SP 4c Semantics → Hall 7

16.45 Semantic Parsing as Machine Translation Jacob Andreas, Andreas Vlachos and Stephen Clark

17.05 A Relatedness Benchmark to Test the Role of Determiners in Compositional Distributional Semantics Raffaella Bernardi, Georgiana Dinu, Marco Marelli and Marco Baroni

17.25 An Empirical Study on Uncertainty Identification in Social Media Context zhongyu wei, Junwen Chen, Wei Gao, Binyang Li, Lanjun Zhou and Kam-fai Wong

17.45 PARMA: A Predicate Argument Aligner Travis Wolfe, Benjamin Van Durme, Mark Dredze, Nicholas Andrews, Charley Beller, Chris Callison-Burch, Jay DeYoung, Justin Snyder, Jonathan Weese, Tan Xu and Xuchen Yao


26

SP 4d Discourse, Coreference and Pragmatics → Hall 8 16.45 Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation Or Biran and Kathleen McKeown

17.05 Implicatures and Nested Beliefs in Approximate Decentralized-POMDPs Adam Vogel, Christopher Potts and Dan Jurafsky

17.25 Domain-Specific Coreference Resolution with Lexicalized Features Nathan Gilbert and Ellen Riloff

17.45 Learning to Order Natural Language Texts Jiwei Tan, Xiaojun Wan and Jianguo Xiao

SP 4e Syntax and Parsing → Hall 10

16.45 Universal Dependency Annotation for Multilingual Parsing Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Tackstrom, Claudia Bedini, Núria Bertomeu Castelló and Jungmee Lee

17.05 An Empirical Examination of Challenges in Chinese Parsing Jonathan K. Kummerfeld, Daniel Tse, James R. Curran and Dan Klein

17.25 Joint Inference for Heterogeneous Dependency Parsing Guangyou Zhou and Jun Zhao

17.45 Easy-First POS Tagging and Dependency Parsing with Beam Search Ji Ma, Jingbo Zhu, Tong Xiao and Nan Yang

27

SHORT PAPERS

SP 4a Machine Translation: Statistical Models → Hall 3

16.45 Translating Dialectal Arabic to English Hassan Sajjad, Kareem Darwish and Yonatan Belinkov

17.05 Exact Maximum Inference for the Fertility Hidden Markov Model Chris Quirk

17.25 A Tale about PRO and Monsters Preslav Nakov, Francisco Guzman and Stephan Vogel

17.45 Supervised Model Learning with Feature Grouping based on a Discrete Constraint Jun Suzuki and Masaaki Nagata


16.45 Exploiting Topic-based Twitter Sentiment for Stock Prediction Jianfeng Si, Arjun Mukherjee, Bing Liu, Qing Li, Huayi Li and xiaotie Deng

17.05 Learning Entity Representation for Entity Disambiguation Zhengyan He, Shujie Liu, Mu Li, Ming Zhou, Houfeng Wang and Longkai Zhang

17.25 Natural Language Models for Predicting Programming Comments Dana Movshovitz-Attias and William Cohen

17.45 Paraphrasing Adaptation for Web Search Ranking Chenguang Wang, Nan Duan, Ming Zhou and Ming Zhang

SP 4c Semantics → Hall 7

16.45 Semantic Parsing as Machine Translation Jacob Andreas, Andreas Vlachos and Stephen Clark

17.05 A Relatedness Benchmark to Test the Role of Determiners in Compositional Distributional Semantics Raffaella Bernardi, Georgiana Dinu, Marco Marelli and Marco Baroni

17.25 An Empirical Study on Uncertainty Identification in Social Media Context zhongyu wei, Junwen Chen, Wei Gao, Binyang Li, Lanjun Zhou and Kam-fai Wong

17.45 PARMA: A Predicate Argument Aligner Travis Wolfe, Benjamin Van Durme, Mark Dredze, Nicholas Andrews, Charley Beller, Chris Callison-Burch, Jay DeYoung, Justin Snyder, Jonathan Weese, Tan Xu and Xuchen Yao


26

SP 4d Discourse, Coreference and Pragmatics → Hall 8 16.45 Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation Or Biran and Kathleen McKeown

17.05 Implicatures and Nested Beliefs in Approximate Decentralized-POMDPs Adam Vogel, Christopher Potts and Dan Jurafsky

17.25 Domain-Specific Coreference Resolution with Lexicalized Features Nathan Gilbert and Ellen Riloff

17.45 Learning to Order Natural Language Texts Jiwei Tan, Xiaojun Wan and Jianguo Xiao

SP 4e Syntax and Parsing → Hall 10

16.45 Universal Dependency Annotation for Multilingual Parsing Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Tackstrom, Claudia Bedini, Núria Bertomeu Castelló and Jungmee Lee

17.05 An Empirical Examination of Challenges in Chinese Parsing Jonathan K. Kummerfeld, Daniel Tse, James R. Curran and Dan Klein

17.25 Joint Inference for Heterogeneous Dependency Parsing Guangyou Zhou and Jun Zhao

17.45 Easy-First POS Tagging and Dependency Parsing with Beam Search Ji Ma, Jingbo Zhu, Tong Xiao and Nan Yang

27

POSTER SESSIONS

POSTER SESSION A: August 5th, 18.30 – 19.45, 2nd and 3rd Floors

Cognitive Modelling and Psycholinguistics → 3rd Floor, East

SP 2469 3rd Floor, East Arguments and Modifiers from the Learner's Perspective Leon Bergen, Timothy O'Donnell and Edward Gibson

Dialogue and Interactive Systems → 3rd Floor, West SP 2515 3rd Floor, West Benefactive/Malefactive Event and Writer Attitude Annotation Lingjia Deng, Yoonjung Choi and Janyce Wiebe

LP 361 3rd Floor, West Discriminative State Tracking for Spoken Dialog Systems Angeliki Metallinou, Dan Bohus and Jason Williams Discourse, Coreference and Pragmatics → 2nd Floor, West

SP 2419 2nd Floor, West GuiTAR-based Pronominal Anaphora Resolution in Bengali Apurbalal Senapati and Utpal Garain LP 150 2nd Floor, West Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition Man Lan, Yu Xu and Zhengyu Niu

LP 166 2nd Floor, West Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis Shafiq Joty, Giuseppe Carenini, Raymond Ng and Yashar Mehdad LP 442 2nd Floor, West Improving Pairwise Coreference Models through Feature Space Hierarchy Learning Emmanuel Lassalle and Pascal Denis

Evaluation Methods → 2nd Floor, West

SP 2345 2nd Floor, West A Decade of Automatic Content Evaluation of News Summaries: Reassessing the State of the Art Peter A. Rankel, John M. Conroy, Hoa Trang Dang and Ani Nenkova


28

SP 2358 2nd Floor, West On the Predictability of Human Assessment: when Matrix Completion Meets NLP Evaluation Guillaume Wisniewski

SP 2458 2nd Floor, West Automated Pyramid Scoring of Summaries using Distributional Semantics Rebecca J. Passonneau, Emily Chen, Dolores Perin and Weiwei Guo Information Retrieval → 3rd Floor, East

SP 2178 3rd Floor, East Are Semantically Coherent Topic Models Useful for Ad Hoc Information Retrieval? Romain Deveaud, Eric SanJuan and Patrice Bellot SP 2262 3rd Floor, East Post-Retrieval Clustering Using Third-Order Similarity Measures Jose G. Moreno, Gaël Dias and Guillaume Cleuziou SP 2198 3rd Floor, East Automatic Coupling of Answer Extraction and Information Retrieval Xuchen Yao, Benjamin Van Durme and Peter Clark LP 381 3rd Floor, East Feature-based Selection of Dependency Paths in Ad Hoc Information Retrieval K. Tamsin Maxwell, Jon Oberlander and W. Bruce Croft

Language Resources → 3rd Floor, East

SP 2310 3rd Floor, East IndoNet: A Multilingual Lexical Knowledge Network for Indian Languages Brijesh Bhatt, Lahari Poddar and Pushpak Bhattacharyya SP 2327 3rd Floor, East Building Japanese Textual Entailment Specialized Data Sets for Inference of Basic Sentence Relations Kimi Kaneko, Yusuke Miyao and Daisuke Bekki

SP 2452 3rd Floor, East Building Comparable Corpora based on Bilingual LDA Model Zede Zhu, Miao Li, Lei Chen and Zhenxin Yang

LP 219 3rd Floor, East Coordination Structures in Dependency Treebanks Zdenek Zabokrtsky, Jan Stepanek, Martin Popel, Daniel Zeman and David Marecek

LP 277 3rd Floor, East GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web Flavio De Benedictis, Stefano Faralli and Roberto Navigli

29

POSTER SESSIONS

POSTER SESSION A: August 5th, 18.30 – 19.45, 2nd and 3rd Floors

Cognitive Modelling and Psycholinguistics → 3rd Floor, East

SP 2469 3rd Floor, East Arguments and Modifiers from the Learner's Perspective Leon Bergen, Timothy O'Donnell and Edward Gibson

Dialogue and Interactive Systems → 3rd Floor, West SP 2515 3rd Floor, West Benefactive/Malefactive Event and Writer Attitude Annotation Lingjia Deng, Yoonjung Choi and Janyce Wiebe

LP 361 3rd Floor, West Discriminative State Tracking for Spoken Dialog Systems Angeliki Metallinou, Dan Bohus and Jason Williams Discourse, Coreference and Pragmatics → 2nd Floor, West

SP 2419 2nd Floor, West GuiTAR-based Pronominal Anaphora Resolution in Bengali Apurbalal Senapati and Utpal Garain LP 150 2nd Floor, West Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition Man Lan, Yu Xu and Zhengyu Niu

LP 166 2nd Floor, West Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis Shafiq Joty, Giuseppe Carenini, Raymond Ng and Yashar Mehdad LP 442 2nd Floor, West Improving Pairwise Coreference Models through Feature Space Hierarchy Learning Emmanuel Lassalle and Pascal Denis

Evaluation Methods → 2nd Floor, West

SP 2345 2nd Floor, West A Decade of Automatic Content Evaluation of News Summaries: Reassessing the State of the Art Peter A. Rankel, John M. Conroy, Hoa Trang Dang and Ani Nenkova


28

SP 2358 2nd Floor, West On the Predictability of Human Assessment: when Matrix Completion Meets NLP Evaluation Guillaume Wisniewski

SP 2458 2nd Floor, West Automated Pyramid Scoring of Summaries using Distributional Semantics Rebecca J. Passonneau, Emily Chen, Dolores Perin and Weiwei Guo Information Retrieval → 3rd Floor, East

SP 2178 3rd Floor, East Are Semantically Coherent Topic Models Useful for Ad Hoc Information Retrieval? Romain Deveaud, Eric SanJuan and Patrice Bellot SP 2262 3rd Floor, East Post-Retrieval Clustering Using Third-Order Similarity Measures Jose G. Moreno, Gaël Dias and Guillaume Cleuziou SP 2198 3rd Floor, East Automatic Coupling of Answer Extraction and Information Retrieval Xuchen Yao, Benjamin Van Durme and Peter Clark LP 381 3rd Floor, East Feature-based Selection of Dependency Paths in Ad Hoc Information Retrieval K. Tamsin Maxwell, Jon Oberlander and W. Bruce Croft

Language Resources → 3rd Floor, East

SP 2310 3rd Floor, East IndoNet: A Multilingual Lexical Knowledge Network for Indian Languages Brijesh Bhatt, Lahari Poddar and Pushpak Bhattacharyya SP 2327 3rd Floor, East Building Japanese Textual Entailment Specialized Data Sets for Inference of Basic Sentence Relations Kimi Kaneko, Yusuke Miyao and Daisuke Bekki

SP 2452 3rd Floor, East Building Comparable Corpora based on Bilingual LDA Model Zede Zhu, Miao Li, Lei Chen and Zhenxin Yang

LP 219 3rd Floor, East Coordination Structures in Dependency Treebanks Zdenek Zabokrtsky, Jan Stepanek, Martin Popel, Daniel Zeman and David Marecek

LP 277 3rd Floor, East GlossBoot: Bootstrapping Multilingual Domain Glossaries from the Web Flavio De Benedictis, Stefano Faralli and Roberto Navigli

29

LP 383 3rd Floor, East Collective Annotation of Linguistic Resources: Basic Principles and a Formal Model Ulle Endriss and Raquel Fernandez

LP 69 3rd Floor, East ParGramBank: The ParGram Parallel Treebank Sebastian Sulger, Miriam Butt, Tracy Holloway King, Paul Meurer, Tibor Laczkó, György Rákosi, Cheikh Bamba Dione, Helge Dyvik, Victoria Rosén, Koenraad De Smedt, Agnieszka Patejuk, Ozlem Cetinoglu, I Wayan Arka and Meladel Mistica

Lexical Semantics and Ontologies → 2nd Floor, West

SP 2277 2nd Floor, West Using Lexical Expansion to Learn Inference Rules from Sparse Data Oren Melamud, Ido Dagan, Jacob Goldberger and Idan Szpektor

SP 2317 2nd Floor, West Mining Equivalent Relations from Linked Data Ziqi Zhang, Anna Lisa Gentile, Isabelle Augenstein, Eva Blomqvist and Fabio Ciravegna

LP 391 2nd Floor, West Identifying Bad Semantic Neighbors for Improving Distributional Thesauri Olivier Ferret

LP 84 2nd Floor, West Models of Semantic Representation with Visual Attributes Carina Silberer, Vittorio Ferrari and Mirella Lapata

Low Resource Language Processing → 2nd Floor, West

SP 2034 2nd Floor, West Context-Dependent Multilingual Lexical Lookup for Under-Resourced Languages Lian Tze Lim, Lay-Ki Soon, Tek Yong Lim, Enya Kong Tang and Bali Ranaivo-Malançon

SP 2045 2nd Floor, West Sorani Kurdish versus Kurmanji Kurdish: An Empirical Comparison Kyumars Sheykh Esmaili and Shahin Salavati

SP 2500 2nd Floor, West Enhanced and Portable Dependency Projection Algorithms Using Interlinear Glossed Text Ryan Georgi, Fei Xia and William D. Lewis

SP 2554 2nd Floor, West Cross-lingual Projections between Languages from Different Families Mo Yu, Tiejun Zhao, Yalong Bai, Hao Tian and Dianhai Yu

SP 2627 2nd Floor, West Using Context Vectors in Improving a Machine Translation System with Bridge Language Samira Tofighi Zahabi, Somayeh Bakhshaei and Shahram Khadivi

POSTER SESSIONS A

30

LP 14 2nd Floor, West Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages Dan Garrette, Jason Mielens and Jason Baldridge

Machine Translation: Methods, Applications and Evaluations → 3rd Floor, West

SP 2003 3rd Floor, West Task Alternation in Parallel Sentence Retrieval for Twitter Translation Felix Hieber, Laura Jehl and Stefan Riezler

SP 2041 3rd Floor, West Sign Language Lexical Recognition With Propositional Dynamic Logic Arturo Curiel and Christophe Collet SP 2084 3rd Floor, West Stacking for Statistical Machine Translation Majid Razmara and Anoop Sarkar SP 2251 3rd Floor, West Bilingual Data Cleaning for SMT using Graph-based Random Walk Lei Cui, Dongdong Zhang, Shujie Liu, Mu Li and Ming Zhou

SP 2306 3rd Floor, West Automatically Predicting Sentence Translation Difficulty Abhijit Mishra and Pushpak Bhattacharyya

SP 2388 3rd Floor, West Learning to Prune: Context-Sensitive Pruning for Syntactic MT Wenduan Xu, Yue Zhang, Philip Williams and Philipp Koehn

SP 2434 3rd Floor, West A Novel Graph-based Compact Representation of Word Alignment Zhaopeng Tu, Qun Liu and Shouxun Lin

SP 2471 3rd Floor, West Stem Translation with Affix-based Rule Selection for Agglutinative Languages Zhiyang Wang, Yajuan Lv, Meng Sun and Qun Liu SP 2556 3rd Floor, West A Novel Translation Framework-based on Rhetorical Structure Theory Mei Tu, Yu Zhou and Chengqing Zong

SP 2631 3rd Floor, West Improving Machine Translation by Training Against an Automatic Semantic Frame-based Evaluation Metric Chi-kiu Lo, Karteek Addanki, Markus Saers and Dekai Wu LP 338 3rd Floor, West Using Subcategorization Knowledge to Improve Case Prediction for Translation to German Marion Weller, Alexander Fraser and Sabine Schulte im Walde

31

LP 383 3rd Floor, East Collective Annotation of Linguistic Resources: Basic Principles and a Formal Model Ulle Endriss and Raquel Fernandez

LP 69 3rd Floor, East ParGramBank: The ParGram Parallel Treebank Sebastian Sulger, Miriam Butt, Tracy Holloway King, Paul Meurer, Tibor Laczkó, György Rákosi, Cheikh Bamba Dione, Helge Dyvik, Victoria Rosén, Koenraad De Smedt, Agnieszka Patejuk, Ozlem Cetinoglu, I Wayan Arka and Meladel Mistica

Lexical Semantics and Ontologies → 2nd Floor, West

SP 2277 2nd Floor, West Using Lexical Expansion to Learn Inference Rules from Sparse Data Oren Melamud, Ido Dagan, Jacob Goldberger and Idan Szpektor

SP 2317 2nd Floor, West Mining Equivalent Relations from Linked Data Ziqi Zhang, Anna Lisa Gentile, Isabelle Augenstein, Eva Blomqvist and Fabio Ciravegna

LP 391 2nd Floor, West Identifying Bad Semantic Neighbors for Improving Distributional Thesauri Olivier Ferret

LP 84 2nd Floor, West Models of Semantic Representation with Visual Attributes Carina Silberer, Vittorio Ferrari and Mirella Lapata

Low Resource Language Processing → 2nd Floor, West

SP 2034 2nd Floor, West Context-Dependent Multilingual Lexical Lookup for Under-Resourced Languages Lian Tze Lim, Lay-Ki Soon, Tek Yong Lim, Enya Kong Tang and Bali Ranaivo-Malançon

SP 2045 2nd Floor, West Sorani Kurdish versus Kurmanji Kurdish: An Empirical Comparison Kyumars Sheykh Esmaili and Shahin Salavati

SP 2500 2nd Floor, West Enhanced and Portable Dependency Projection Algorithms Using Interlinear Glossed Text Ryan Georgi, Fei Xia and William D. Lewis

SP 2554 2nd Floor, West Cross-lingual Projections between Languages from Different Families Mo Yu, Tiejun Zhao, Yalong Bai, Hao Tian and Dianhai Yu

SP 2627 2nd Floor, West Using Context Vectors in Improving a Machine Translation System with Bridge Language Samira Tofighi Zahabi, Somayeh Bakhshaei and Shahram Khadivi

POSTER SESSIONS A

30

LP 14 2nd Floor, West Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages Dan Garrette, Jason Mielens and Jason Baldridge

Machine Translation: Methods, Applications and Evaluations → 3rd Floor, West

SP 2003 3rd Floor, West Task Alternation in Parallel Sentence Retrieval for Twitter Translation Felix Hieber, Laura Jehl and Stefan Riezler

SP 2041 3rd Floor, West Sign Language Lexical Recognition With Propositional Dynamic Logic Arturo Curiel and Christophe Collet SP 2084 3rd Floor, West Stacking for Statistical Machine Translation Majid Razmara and Anoop Sarkar SP 2251 3rd Floor, West Bilingual Data Cleaning for SMT using Graph-based Random Walk Lei Cui, Dongdong Zhang, Shujie Liu, Mu Li and Ming Zhou

SP 2306 3rd Floor, West Automatically Predicting Sentence Translation Difficulty Abhijit Mishra and Pushpak Bhattacharyya

SP 2388 3rd Floor, West Learning to Prune: Context-Sensitive Pruning for Syntactic MT Wenduan Xu, Yue Zhang, Philip Williams and Philipp Koehn

SP 2434 3rd Floor, West A Novel Graph-based Compact Representation of Word Alignment Zhaopeng Tu, Qun Liu and Shouxun Lin

SP 2471 3rd Floor, West Stem Translation with Affix-based Rule Selection for Agglutinative Languages Zhiyang Wang, Yajuan Lv, Meng Sun and Qun Liu SP 2556 3rd Floor, West A Novel Translation Framework-based on Rhetorical Structure Theory Mei Tu, Yu Zhou and Chengqing Zong

SP 2631 3rd Floor, West Improving Machine Translation by Training Against an Automatic Semantic Frame-based Evaluation Metric Chi-kiu Lo, Karteek Addanki, Markus Saers and Dekai Wu LP 338 3rd Floor, West Using Subcategorization Knowledge to Improve Case Prediction for Translation to German Marion Weller, Alexander Fraser and Sabine Schulte im Walde

31

LP 388 3rd Floor, West Name-aware Machine Translation Haibo Li, Jing Zheng, Heng Ji, Qi Li and Wen Wang LP 468 3rd Floor, West Decipherment Complexity in 1:1 Substitution Ciphers Malte Nuhn and Hermann Ney

LP 8 3rd Floor, West Non-Monotonic Sentence Alignment via Semisupervised Learning Xiaojun Quan, Chunyu Kit and Yan Song

Multilinguality → 2nd Floor, East

SP 2144 2nd Floor, East Enriching Entity Translation Discovery using Selective Temporality Gae-won You, Young-rok Cha, Jinhan Kim and Seung-won Hwang

SP 2364 2nd Floor, East Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling Heike Adel, Ngoc Thang Vu and Tanja Schultz

SP 2495 2nd Floor, East Latent Semantic Matching: Application to Cross-language Text Categorization without Alignment Information Tsutomu Hirao, Tomoharu Iwata and Masaaki Nagata LP 571 2nd Floor, East Bootstrapping Entity Translation on Weakly Comparable Corpora Taesung Lee and Seung-won Hwang

LP 237 2nd Floor, East Bridging Languages through Etymology: The Case of Cross-language Text Categorization Vivi Nastase and Carlo Strapparava

LP 179 2nd Floor, East Transfer Learning-based Cross-lingual Knowledge Extraction for Wikipedia Zhigang Wang, Zhixing Li, Juanzi Li, Jie Tang, Jeff Z. Pan

NLP Applications → 2nd Floor, West

SP 2022 2nd Floor, West TopicSpam: a Topic-Model based Approach for Spam Detection Jiwei Li and Sujian Li

SP 2136 2nd Floor, West Identifying Semantic Neighborhoods Chris Quirk and Pallavi Choudhury

POSTER SESSIONS A

32

SP 2197 2nd Floor, West Unsupervised Joke Generation from Big Data Sasa Petrovic and David Matthews

SP 2381 2nd Floor, West Modeling of Term-distance and Term-occurrence Information for Improving N-gram Language Model Performance Tze Yuang Chong, Rafael E. Banchs, Eng Siong Chng and Haizhou Li

SP 2590 2nd Floor, West Discriminative Approach to Fill-in-the-Blank Quiz Generation for Language Learners Keisuke Sakaguchi, Yuki Arase and Mamoru Komachi

LP 369 2nd Floor, West Creating Similarity: Lateral Thinking for Vertical Similarity Judgments Tony Veale and Guofu Li

LP 611 2nd Floor, West Discovering User Interactions in Ideological Discussions Arjun Mukherjee and Bing Liu

NLP and Creativity → 3rd Floor, East

SP 2316 3rd Floor, East “Let Everything Turn Well in Your Wife”: Generation of Adult Humor Using Lexical Constraints Alessandro Valitutti, Hannu Toivonen, Antoine Doucet and Jukka Toivanen SP 2501 3rd Floor, East Random Walk Factoid Annotation for Collective Discourse Ben King, Rahul Jha and Dragomir Radev

LP 91 3rd Floor, East Multilingual Affect Polarity and Valence Prediction in Metaphor-Rich Texts Zornitsa Kozareva

NLP for the Languages of Central and Eastern Europe and the Balkans → 2nd Floor, East

SP 2235 2nd Floor, East Identifying English and Hungarian Light Verb Constructions: A Contrastive Approach Veronika Vincze, István T. Nagy and Richárd Farkas

SP 2241 2nd Floor, East English-to-Russian MT Evaluation Campaign Pavel Braslavski, Alexander Beloborodov, Maxim Khalilov and Serge Sharoff

LP 264 2nd Floor, East Large Tagset Labeling Using Feed Forward Neural Networks. Case Study on Romanian Language Tiberiu Boros, Radu Ion and Dan Tufis

33

LP 388 3rd Floor, West Name-aware Machine Translation Haibo Li, Jing Zheng, Heng Ji, Qi Li and Wen Wang LP 468 3rd Floor, West Decipherment Complexity in 1:1 Substitution Ciphers Malte Nuhn and Hermann Ney

LP 8 3rd Floor, West Non-Monotonic Sentence Alignment via Semisupervised Learning Xiaojun Quan, Chunyu Kit and Yan Song

Multilinguality → 2nd Floor, East

SP 2144 2nd Floor, East Enriching Entity Translation Discovery using Selective Temporality Gae-won You, Young-rok Cha, Jinhan Kim and Seung-won Hwang

SP 2364 2nd Floor, East Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling Heike Adel, Ngoc Thang Vu and Tanja Schultz

SP 2495 2nd Floor, East Latent Semantic Matching: Application to Cross-language Text Categorization without Alignment Information Tsutomu Hirao, Tomoharu Iwata and Masaaki Nagata LP 571 2nd Floor, East Bootstrapping Entity Translation on Weakly Comparable Corpora Taesung Lee and Seung-won Hwang

LP 237 2nd Floor, East Bridging Languages through Etymology: The Case of Cross-language Text Categorization Vivi Nastase and Carlo Strapparava

LP 179 2nd Floor, East Transfer Learning-based Cross-lingual Knowledge Extraction for Wikipedia Zhigang Wang, Zhixing Li, Juanzi Li, Jie Tang, Jeff Z. Pan

NLP Applications → 2nd Floor, West

SP 2022 2nd Floor, West TopicSpam: a Topic-Model based Approach for Spam Detection Jiwei Li and Sujian Li

SP 2136 2nd Floor, West Identifying Semantic Neighborhoods Chris Quirk and Pallavi Choudhury

POSTER SESSIONS A

32

SP 2197 2nd Floor, West Unsupervised Joke Generation from Big Data Sasa Petrovic and David Matthews

SP 2381 2nd Floor, West Modeling of Term-distance and Term-occurrence Information for Improving N-gram Language Model Performance Tze Yuang Chong, Rafael E. Banchs, Eng Siong Chng and Haizhou Li

SP 2590 2nd Floor, West Discriminative Approach to Fill-in-the-Blank Quiz Generation for Language Learners Keisuke Sakaguchi, Yuki Arase and Mamoru Komachi

LP 369 2nd Floor, West Creating Similarity: Lateral Thinking for Vertical Similarity Judgments Tony Veale and Guofu Li

LP 611 2nd Floor, West Discovering User Interactions in Ideological Discussions Arjun Mukherjee and Bing Liu

NLP and Creativity → 3rd Floor, East

SP 2316 3rd Floor, East “Let Everything Turn Well in Your Wife”: Generation of Adult Humor Using Lexical Constraints Alessandro Valitutti, Hannu Toivonen, Antoine Doucet and Jukka Toivanen SP 2501 3rd Floor, East Random Walk Factoid Annotation for Collective Discourse Ben King, Rahul Jha and Dragomir Radev

LP 91 3rd Floor, East Multilingual Affect Polarity and Valence Prediction in Metaphor-Rich Texts Zornitsa Kozareva

NLP for the Languages of Central and Eastern Europe and the Balkans → 2nd Floor, East

SP 2235 2nd Floor, East Identifying English and Hungarian Light Verb Constructions: A Contrastive Approach Veronika Vincze, István T. Nagy and Richárd Farkas

SP 2241 2nd Floor, East English-to-Russian MT Evaluation Campaign Pavel Braslavski, Alexander Beloborodov, Maxim Khalilov and Serge Sharoff

LP 264 2nd Floor, East Large Tagset Labeling Using Feed Forward Neural Networks. Case Study on Romanian Language Tiberiu Boros, Radu Ion and Dan Tufis

33

LP 427 2nd Floor, East Learning to Lemmatise Polish Noun Phrases Adam Radziszewski

NLP for the Web and Social Media → 2nd Floor, East

LP 276 2nd Floor, East Using Conceptual Class Attributes to Characterize Social Media Users Shane Bergsma and Benjamin Van Durme LP 4 2nd Floor, East The Impact of Topic Bias on Quality Flaw Prediction in Wikipedia Oliver Ferschke, Iryna Gurevych and Marc Rittberger

LP 111 2nd Floor, East Mining Informal Language from Chinese Microtext: Joint Word Recognition and Segmentation Aobo Wang and Min-Yen Kan

LP 328 2nd Floor, East Generating Synthetic Comparable Questions for News Articles Oleg Rokhlenko and Idan Szpektor

Spoken Language Processing → 2nd Floor, East

SP 2521 2nd Floor, East Broadcast News Story Segmentation Using Manifold Learning on Latent Topic Distributions Xiaoming Lu, Lei Xie, Cheung-Chi Leung, Bin Ma and Haizhou Li

SP 2568 2nd Floor, East Is Word-to-Phone Mapping Better than Phone-Phone Mapping for Handling English Words? Naresh Kumar Elluru, Anandaswarup Vadapalli, Raghavendra Elluru and Kishore Prahallad

LP 249 2nd Floor, East Punctuation Prediction with Transition-based Parsing Dongdong Zhang, Shuangzhi Wu, Nan Yang and Mu Li

TACL → 2nd Floor, West

LP 38 2nd Floor, West Learning to Translate with Products of Novices: Teaching MT with Competitive Challenge Problems Adam Lopez, Matt Post, Chris Callison-Burch, Jonathan Weese, Juri Ganitkevitch, Narges Ahmidi, Olivia Buzek, Leah Hanson, Beenish Jamil, Matthias Lee, Ya-Ting Lin, Henry Pao, Fatima Rivera, Leili Shahriyari, Debu Sinha, Adam Teichert, Stephen Wampler, Michael Weinberger, Daguang Xu, Lin Yang, Shang Zhao

LP 20 2nd Floor, West Minimally-Supervised Morphological Segmentation using Adaptor Grammars Kairit Sirts, Sharon Goldwater

POSTER SESSIONS A

34

LP 58 2nd Floor, West Unsupervised Tree Induction for Tree-based Translation Feifei Zhai, Jiajun Zhang, Yu Zhou, Chengqing Zong

Word Segmentation → 2nd Floor, East

SP 2539 2nd Floor, East An Improved MDL-based Compression Algorithm for Unsupervised Word Segmentation Ruey-Cheng Chen SP 2141 2nd Floor, East Co-regularizing Character-based and Word-based Models for Semi-supervised Chinese Word Segmentation Xiaodong Zeng, Derek F. Wong, Lidia S. Chao and Isabel Trancoso

SP 2283 2nd Floor, East Improving Chinese Word Segmentation on Micro-blog Using Rich Punctuations Longkai Zhang, Li Li, Zhengyan He, Houfeng Wang and Ni Sun

SP 2481 2nd Floor, East Accurate Word Segmentation using Transliteration and Language Model Projection Masato Hagiwara

LP 178 2nd Floor, East Discriminative Learning with Natural Annotations: Word Segmentation as a Case Study Wenbin Jiang, Meng Sun, Yajuan Lv, Yating Yang and Qun Liu

LP 170 2nd Floor, East Graph-based Semi-Supervised Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging Xiaodong Zeng, Derek F. Wong, Lidia S. Chao and Isabel Trancoso

35

LP 427 2nd Floor, East Learning to Lemmatise Polish Noun Phrases Adam Radziszewski

NLP for the Web and Social Media → 2nd Floor, East

LP 276 2nd Floor, East Using Conceptual Class Attributes to Characterize Social Media Users Shane Bergsma and Benjamin Van Durme LP 4 2nd Floor, East The Impact of Topic Bias on Quality Flaw Prediction in Wikipedia Oliver Ferschke, Iryna Gurevych and Marc Rittberger

LP 111 2nd Floor, East Mining Informal Language from Chinese Microtext: Joint Word Recognition and Segmentation Aobo Wang and Min-Yen Kan

LP 328 2nd Floor, East Generating Synthetic Comparable Questions for News Articles Oleg Rokhlenko and Idan Szpektor

Spoken Language Processing → 2nd Floor, East

SP 2521 2nd Floor, East Broadcast News Story Segmentation Using Manifold Learning on Latent Topic Distributions Xiaoming Lu, Lei Xie, Cheung-Chi Leung, Bin Ma and Haizhou Li

SP 2568 2nd Floor, East Is Word-to-Phone Mapping Better than Phone-Phone Mapping for Handling English Words? Naresh Kumar Elluru, Anandaswarup Vadapalli, Raghavendra Elluru and Kishore Prahallad

LP 249 2nd Floor, East Punctuation Prediction with Transition-based Parsing Dongdong Zhang, Shuangzhi Wu, Nan Yang and Mu Li

TACL → 2nd Floor, West

LP 38 2nd Floor, West Learning to Translate with Products of Novices: Teaching MT with Competitive Challenge Problems Adam Lopez, Matt Post, Chris Callison-Burch, Jonathan Weese, Juri Ganitkevitch, Narges Ahmidi, Olivia Buzek, Leah Hanson, Beenish Jamil, Matthias Lee, Ya-Ting Lin, Henry Pao, Fatima Rivera, Leili Shahriyari, Debu Sinha, Adam Teichert, Stephen Wampler, Michael Weinberger, Daguang Xu, Lin Yang, Shang Zhao

LP 20 2nd Floor, West Minimally-Supervised Morphological Segmentation using Adaptor Grammars Kairit Sirts, Sharon Goldwater

POSTER SESSIONS A

34

LP 58 2nd Floor, West Unsupervised Tree Induction for Tree-based Translation Feifei Zhai, Jiajun Zhang, Yu Zhou, Chengqing Zong

Word Segmentation → 2nd Floor, East

SP 2539 2nd Floor, East An Improved MDL-based Compression Algorithm for Unsupervised Word Segmentation Ruey-Cheng Chen SP 2141 2nd Floor, East Co-regularizing Character-based and Word-based Models for Semi-supervised Chinese Word Segmentation Xiaodong Zeng, Derek F. Wong, Lidia S. Chao and Isabel Trancoso

SP 2283 2nd Floor, East Improving Chinese Word Segmentation on Micro-blog Using Rich Punctuations Longkai Zhang, Li Li, Zhengyan He, Houfeng Wang and Ni Sun

SP 2481 2nd Floor, East Accurate Word Segmentation using Transliteration and Language Model Projection Masato Hagiwara

LP 178 2nd Floor, East Discriminative Learning with Natural Annotations: Word Segmentation as a Case Study Wenbin Jiang, Meng Sun, Yajuan Lv, Yating Yang and Qun Liu

LP 170 2nd Floor, East Graph-based Semi-Supervised Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging Xiaodong Zeng, Derek F. Wong, Lidia S. Chao and Isabel Trancoso

35

POSTER SESSION B: August 5th, 19.45 - 21.00, 2nd and 3rd Floors

Machine Translation: Statistical Models → 3rd Floor, West

SP� 2127� 3rd Floor, West Bilingual Lexical Cohesion Trigger Model for Document-Level Machine Translation Guosheng Ben, Deyi Xiong, Zhiyang Teng, Yajuan Lü and Qun Liu

SP� 2195� 3rd Floor, West Generalized Reordering Rules for Improved SMT Fei Huang and Cezar Pendus

SP� 2289� 3rd Floor, West A Tightly-coupled Unsupervised Clustering and Bilingual Alignment Model for Transliteration Tingting Li, Tiejun Zhao, Andrew Finch and Chunyue Zhang

SP� 2405� 3rd Floor, West Can Markov Models Over Minimal Translation Units Help Phrase-based SMT? Nadir Durrani, Alexander Fraser, Helmut Schmid, Hieu Hoang and Philipp Koehn

SP� 2527� 3rd Floor, West Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines Kristina Toutanova and Byunggyu Ahn

SP� 2553� 3rd Floor, West Language Independent Connectivity Strength Features for Pivot Translation Ahmed El Kholy and Nizar Habash

SP� 2204� 3rd Floor, West Semantic Roles for String to Tree Machine Translation� Marzieh Bazrafshan and Daniel Gildea�LP� 144� 3rd Floor, West An Infinite Hierarchical Bayesian Model of Phrasal Translation Trevor Cohn and Gholamreza Haffari

LP� 190� 3rd Floor, West Additive Neural Networks for Statistical Machine Translation Lemao Liu, Taro Watanabe, Eiichiro Sumita and Tiejun Zhao Bing Xiang, Xiaoqiang Luo and Bowen Zhou

LP� 211� 3rd Floor, West Hierarchical Phrase Table Combination for Machine Translation Conghui Zhu, Taro Watanabe, Eiichiro Sumita and Tiejun Zhao�

LP� 359� 3rd Floor, West Shallow Local Multi-Bottom-up Tree Transducers in Statistical Machine Translation Fabienne Braune, Nina Seemann, Daniel Quernheim and Andreas Maletti


36

LP� 364� 3rd Floor, West Enlisting the Ghost: Modeling Empty Categories for Machine Translation Bing Xiang, Xiaoqiang Luo and Bowen Zhou

LP� 519� 3rd Floor, West A Multi-Domain Translation Model Framework for Statistical Machine Translation Rico Sennrich, Holger Schwenk and Walid Aransa

LP� 92� 3rd Floor, West Part-of-Speech Induction in Dependency Trees for Statistical Machine Translation Akihiro Tamura, Taro Watanabe, Eiichiro Sumita, Hiroya Takamura and Manabu Okumura�

� Question Answering → 3rd Floor, East

SP� 2258� 3rd Floor, East Minimum Bayes Risk based Answer Re-ranking for Question Answering Nan Duan

SP� 2307� 3rd Floor, East Question Classification Transfer Anne-Laure Ligozat

SP� 2470� 3rd Floor, East Latent Semantic Tensor Indexing for Community-based Question Answering Xipeng Qiu, Le Tian and Xuanjing Huang

LP� 13� 3rd Floor, East Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization Guangyou Zhou, Fang Liu, Yang Liu, Shizhu He and Jun Zhao

� Semantics → 2nd Floor, West

SP� 2082� 2nd Floor, West Measuring Semantic Content in Distributional Vectors Aurelie Herbelot and Mohan Ganesalingam

SP� 2282� 2nd Floor, West Modeling Human Inference Process for Textual Entailment Recognition Hen-Hsen Huang, Kai-Chun Chang and Hsin-Hsi Chen

SP� 2340� 2nd Floor, West Recognizing Partial Textual Entailment Omer Levy, Torsten Zesch, Ido Dagan and Iryna Gurevych

SP 2383� 2nd Floor, West Sentence Level Dialect Identification in Arabic | Heba Elfardy and Mona Diab 37

POSTER SESSION B: August 5th, 19.45 - 21.00, 2nd and 3rd Floors

Machine Translation: Statistical Models → 3rd Floor, West

SP� 2127� 3rd Floor, West Bilingual Lexical Cohesion Trigger Model for Document-Level Machine Translation Guosheng Ben, Deyi Xiong, Zhiyang Teng, Yajuan Lü and Qun Liu

SP� 2195� 3rd Floor, West Generalized Reordering Rules for Improved SMT Fei Huang and Cezar Pendus

SP� 2289� 3rd Floor, West A Tightly-coupled Unsupervised Clustering and Bilingual Alignment Model for Transliteration Tingting Li, Tiejun Zhao, Andrew Finch and Chunyue Zhang

SP� 2405� 3rd Floor, West Can Markov Models Over Minimal Translation Units Help Phrase-based SMT? Nadir Durrani, Alexander Fraser, Helmut Schmid, Hieu Hoang and Philipp Koehn

SP� 2527� 3rd Floor, West Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines Kristina Toutanova and Byunggyu Ahn

SP� 2553� 3rd Floor, West Language Independent Connectivity Strength Features for Pivot Translation Ahmed El Kholy and Nizar Habash

SP� 2204� 3rd Floor, West Semantic Roles for String to Tree Machine Translation� Marzieh Bazrafshan and Daniel Gildea�LP� 144� 3rd Floor, West An Infinite Hierarchical Bayesian Model of Phrasal Translation Trevor Cohn and Gholamreza Haffari

LP� 190� 3rd Floor, West Additive Neural Networks for Statistical Machine Translation Lemao Liu, Taro Watanabe, Eiichiro Sumita and Tiejun Zhao Bing Xiang, Xiaoqiang Luo and Bowen Zhou

LP� 211� 3rd Floor, West Hierarchical Phrase Table Combination for Machine Translation Conghui Zhu, Taro Watanabe, Eiichiro Sumita and Tiejun Zhao�

LP� 359� 3rd Floor, West Shallow Local Multi-Bottom-up Tree Transducers in Statistical Machine Translation Fabienne Braune, Nina Seemann, Daniel Quernheim and Andreas Maletti


36

LP� 364� 3rd Floor, West Enlisting the Ghost: Modeling Empty Categories for Machine Translation Bing Xiang, Xiaoqiang Luo and Bowen Zhou

LP� 519� 3rd Floor, West A Multi-Domain Translation Model Framework for Statistical Machine Translation Rico Sennrich, Holger Schwenk and Walid Aransa

LP� 92� 3rd Floor, West Part-of-Speech Induction in Dependency Trees for Statistical Machine Translation Akihiro Tamura, Taro Watanabe, Eiichiro Sumita, Hiroya Takamura and Manabu Okumura�

� Question Answering → 3rd Floor, East

SP� 2258� 3rd Floor, East Minimum Bayes Risk based Answer Re-ranking for Question Answering Nan Duan

SP� 2307� 3rd Floor, East Question Classification Transfer Anne-Laure Ligozat

SP� 2470� 3rd Floor, East Latent Semantic Tensor Indexing for Community-based Question Answering Xipeng Qiu, Le Tian and Xuanjing Huang

LP� 13� 3rd Floor, East Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization Guangyou Zhou, Fang Liu, Yang Liu, Shizhu He and Jun Zhao

� Semantics → 2nd Floor, West

SP� 2082� 2nd Floor, West Measuring Semantic Content in Distributional Vectors Aurelie Herbelot and Mohan Ganesalingam

SP� 2282� 2nd Floor, West Modeling Human Inference Process for Textual Entailment Recognition Hen-Hsen Huang, Kai-Chun Chang and Hsin-Hsi Chen

SP� 2340� 2nd Floor, West Recognizing Partial Textual Entailment Omer Levy, Torsten Zesch, Ido Dagan and Iryna Gurevych

SP 2383� 2nd Floor, West Sentence Level Dialect Identification in Arabic | Heba Elfardy and Mona Diab 37

SP� 2432� 2nd Floor, West Leveraging Domain-Independent Information for Semantic Parsing Dan Goldwasser and Dan Roth

SP� 2451� 2nd Floor, West A Structured Distributional Semantic Model for Event Co-reference Kartik Goyal, Sujay Kumar Jauhar, Mrinmaya Sachan, Shashank Srivastava, Huiying Li and Eduard Hovy

LP� 31� 2nd Floor, West Improved Lexical Acquisition through DPP-based Verb Clustering Roi Reichart and Anna Korhonen

LP� 404� 2nd Floor, West Semantic Frames to Predict Stock Price Movement Boyi Xie, Rebecca Passonneau, German Creamer and Leon Wu

LP� 478� 2nd Floor, West Density Maximization in Context-Sense Metric Space for All-words WSD Koichi Tanigaki, Mitsuteru Shiba, Tatsuji Munaka and Yoshinori Sagisaka

LP� 549� 2nd Floor, West The Role of Syntax in Vector Space Models of Compositional Semantics Karl Moritz Hermann and Phil Blunsom�

LP� 559� 2nd Floor, West Margin-based Decomposed Amortized Inference Gourab Kundu, Vivek Srikumar and Dan Roth

LP� 590� 2nd Floor, West Semi-Supervised Semantic Tagging of Conversational Understanding using Markov Topic Regression Asli Celikyilmaz, Dilek Hakkani-Tur, Gokhan Tur and Ruhi Sarikaya

LP� 655� 2nd Floor, West Parsing Graphs with Hyperedge Replacement Grammars David Chiang, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan Jones and Kevin Knight

LP� 607� 2nd Floor, West Grounded Unsupervised Semantic Parsing Hoifung Poon�

Sentiment Analysis, Opinion Mining and Text Classification → 2nd Floor, East

SP� 2158� 2nd Floor, East Text Classification from Positive and Unlabeled Data using Misclassified Data Correction Fumiyo Fukumoto, Yoshimi Suzuki and Suguru Matsuyoshi

POSTER SESSIONS B

38

SP� 2183� 2nd Floor, East Character-to-Character Sentiment Analysis in Shakespeare's Plays Eric Nalisnick and Henry Baird

SP� 2308� 2nd Floor, East A Novel Text Classifier – based on Quantum Computation Ding Liu, Xiaofang Yang and Minghu Jiang

SP� 2311� 2nd Floor, East Re-embedding Words Igor Labutov and Hod Lipson

SP� 2397� 2nd Floor, East LABR: A Large Scale Arabic Book Reviews Dataset Mohamed Aly and Amir Atiya

SP� 2408� 2nd Floor, East Generating Recommendation Dialogs by Extracting Information from User Reviews Kevin Reschke, Adam Vogel and Dan Jurafsky

SP� 2462� 2nd Floor, East Exploring Sentiment in Social Media: Bootstrapping Subjectivity Clues from Multilingual Twitter Streams Svitlana Volkova, Theresa Wilson and David Yarowsky

SP� 2479� 2nd Floor, East Joint Modeling of News Reader's and Comment Writer's Emotions Huanhuan Liu, Shoushan Li, Guodong Zhou, Chu-ren Huang and Peifeng Li

SP� 2492� 2nd Floor, East An Annotated Corpus of Quoted Opinions in News Articles Tim O'Keefe, James Curran, Irena Koprinska and Peter Ashwell

SP� 2564� 2nd Floor, East Dual Training and Dual Prediction for Polarity Classification Rui Xia, Tao Wang, Xuelei Hu, Shoushan Li and Chengqing Zong

SP� 2030� 2nd Floor, East Co-Regression for Cross-Language Review Rating Prediction Xiaojun Wan

LP� 149� 2nd Floor, East Automatic Detection of Deception in Child-produced Speech Using Syntactic Complexity Features Maria Yancheva and Frank Rudzicz

LP� 243� 2nd Floor, East Sentiment Relevance Christian Scheible and Hinrich Schütze� 39

SP� 2432� 2nd Floor, West Leveraging Domain-Independent Information for Semantic Parsing Dan Goldwasser and Dan Roth

SP� 2451� 2nd Floor, West A Structured Distributional Semantic Model for Event Co-reference Kartik Goyal, Sujay Kumar Jauhar, Mrinmaya Sachan, Shashank Srivastava, Huiying Li and Eduard Hovy

LP� 31� 2nd Floor, West Improved Lexical Acquisition through DPP-based Verb Clustering Roi Reichart and Anna Korhonen

LP� 404� 2nd Floor, West Semantic Frames to Predict Stock Price Movement Boyi Xie, Rebecca Passonneau, German Creamer and Leon Wu

LP� 478� 2nd Floor, West Density Maximization in Context-Sense Metric Space for All-words WSD Koichi Tanigaki, Mitsuteru Shiba, Tatsuji Munaka and Yoshinori Sagisaka

LP� 549� 2nd Floor, West The Role of Syntax in Vector Space Models of Compositional Semantics Karl Moritz Hermann and Phil Blunsom�

LP� 559� 2nd Floor, West Margin-based Decomposed Amortized Inference Gourab Kundu, Vivek Srikumar and Dan Roth

LP� 590� 2nd Floor, West Semi-Supervised Semantic Tagging of Conversational Understanding using Markov Topic Regression Asli Celikyilmaz, Dilek Hakkani-Tur, Gokhan Tur and Ruhi Sarikaya

LP� 655� 2nd Floor, West Parsing Graphs with Hyperedge Replacement Grammars David Chiang, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan Jones and Kevin Knight

LP� 607� 2nd Floor, West Grounded Unsupervised Semantic Parsing Hoifung Poon�

Sentiment Analysis, Opinion Mining and Text Classification → 2nd Floor, East

SP� 2158� 2nd Floor, East Text Classification from Positive and Unlabeled Data using Misclassified Data Correction Fumiyo Fukumoto, Yoshimi Suzuki and Suguru Matsuyoshi

POSTER SESSIONS B

38

SP� 2183� 2nd Floor, East Character-to-Character Sentiment Analysis in Shakespeare's Plays Eric Nalisnick and Henry Baird

SP� 2308� 2nd Floor, East A Novel Text Classifier – based on Quantum Computation Ding Liu, Xiaofang Yang and Minghu Jiang

SP� 2311� 2nd Floor, East Re-embedding Words Igor Labutov and Hod Lipson

SP� 2397� 2nd Floor, East LABR: A Large Scale Arabic Book Reviews Dataset Mohamed Aly and Amir Atiya

SP� 2408� 2nd Floor, East Generating Recommendation Dialogs by Extracting Information from User Reviews Kevin Reschke, Adam Vogel and Dan Jurafsky

SP� 2462� 2nd Floor, East Exploring Sentiment in Social Media: Bootstrapping Subjectivity Clues from Multilingual Twitter Streams Svitlana Volkova, Theresa Wilson and David Yarowsky

SP� 2479� 2nd Floor, East Joint Modeling of News Reader's and Comment Writer's Emotions Huanhuan Liu, Shoushan Li, Guodong Zhou, Chu-ren Huang and Peifeng Li

SP� 2492� 2nd Floor, East An Annotated Corpus of Quoted Opinions in News Articles Tim O'Keefe, James Curran, Irena Koprinska and Peter Ashwell

SP� 2564� 2nd Floor, East Dual Training and Dual Prediction for Polarity Classification Rui Xia, Tao Wang, Xuelei Hu, Shoushan Li and Chengqing Zong

SP� 2030� 2nd Floor, East Co-Regression for Cross-Language Review Rating Prediction Xiaojun Wan

LP� 149� 2nd Floor, East Automatic Detection of Deception in Child-produced Speech Using Syntactic Complexity Features Maria Yancheva and Frank Rudzicz

LP� 243� 2nd Floor, East Sentiment Relevance Christian Scheible and Hinrich Schütze� 39

LP� 568� 2nd Floor, East Predicting and Eliciting Addressee's Emotion in Online Dialogue Takayuki Hasegawa, Nobuhiro Kaji, Naoki Yoshinaga and Masashi Toyoda

LP� 596� 2nd Floor, East Utterance-Level Multimodal Sentiment Analysis Veronica Perez-Rosas, Rada Mihalcea and Louis-Philippe Morency

LP� 643� 2nd Floor, East Probabilistic Sense Sentiment Similarity through Hidden Emotions Mitra Mohtarami, Man Lan and Chew Lim Tan� �

� Statistical and Machine Learning Methods in NLP → 2nd Floor, East

SP� 2153� 2nd Floor, East Extracting Definitions and Hypernym Relations relying on Syntactic Dependencies and Support Vector Machines Guido Boella and Luigi Di Caro

SP� 2314� 2nd Floor, East Neighbors Help: Bilingual Unsupervised WSD Using Context Sudha Bhingardive, Samiulla Shaikh and Pushpak Bhattacharyya

SP� 2406� 2nd Floor, East Reducing Annotation Effort for Quality Estimation via Active Learning Daniel Beck, Lucia Specia and Trevor Cohn

SP� 2461� 2nd Floor, East Ensemble Reranking with Linguistic and Semantic Features for Arabic Character Recognition Nadi Tomeh, Nizar Habash, Ryan Roth, Noura Farra, Pradeep Dasigi and Mona Diab

LP� 132� 2nd Floor, East A User-centric Model of Voting Intention from Social Media Vasileios Lampos, Daniel Preotiuc-Pietro and Trevor Cohn

�� Summarization and Generation → 3rd Floor, East

SP� 2047� 3rd Floor, East Evolutionary Hierarchical Dirichlet Process for Timeline Summarization Jiwei Li and Sujian Li

SP� 2189� 3rd Floor, East Using Integer Linear Programming in Concept-to-Text Generation to Produce More Compact Texts Gerasimos Lampouras and Ion Androutsopoulos

POSTER SESSIONS B

40

SP� 2509� 3rd Floor, East Sequential Summarization: A New Application for Timely Updated Twitter Trending Topics Dehong Gao, Wenjie Li and Renxian Zhang

SP� 2533� 3rd Floor, East A System for Summarizing Scientific Topics Starting from Keywords Rahul Jha, Amjad Abu-Jbara and Dragomir Radev

LP� 481� 3rd Floor, East Using Supervised Bigram-based ILP for Extractive Summarization Chen Li, Xian Qian and Yang Liu

LP� 505� 3rd Floor, East Summarization Through Submodularity and Dispersion Anirban Dasgupta, Ravi Kumar and Sujith Ravi

LP� 510� 3rd Floor, East Subtree Extractive Summarization via Submodular Maximization Hajime Morita, Ryohei Sasano, Hiroya Takamura and Manabu Okumura� �

� Syntax and Parsing → 2nd Floor, West

SP� 2181� 2nd Floor, West A Unified Morpho-Syntactic Scheme of Stanford Dependencies Reut Tsarfaty

SP� 2294� 2nd Floor, West Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain data Xuezhe Ma and Fei Xia

SP� 2300� 2nd Floor, West Iterative Transformation of Annotation Guidelines for Constituency Parsing Xiang Li, Wenbin Jiang, Yajuan Lv and Qun Liu

SP� 2389� 2nd Floor, West Nonparametric Bayesian Inference and Cubic-time Parsing for Tree-adjoining Grammars Elif Yamangil

SP� 2403� 2nd Floor, West Using CCG categories to improve Hindi dependency parsing Bharat Ram Ambati, Tejaswini Deoskar and Mark Steedman

SP� 2433 The Effect of Higher-Order Dependency Features in Discriminative Phrase-Structure Parsing Greg Coppola and Mark Steedman

41

LP� 568� 2nd Floor, East Predicting and Eliciting Addressee's Emotion in Online Dialogue Takayuki Hasegawa, Nobuhiro Kaji, Naoki Yoshinaga and Masashi Toyoda

LP� 596� 2nd Floor, East Utterance-Level Multimodal Sentiment Analysis Veronica Perez-Rosas, Rada Mihalcea and Louis-Philippe Morency

LP� 643� 2nd Floor, East Probabilistic Sense Sentiment Similarity through Hidden Emotions Mitra Mohtarami, Man Lan and Chew Lim Tan� �

� Statistical and Machine Learning Methods in NLP → 2nd Floor, East

SP� 2153� 2nd Floor, East Extracting Definitions and Hypernym Relations relying on Syntactic Dependencies and Support Vector Machines Guido Boella and Luigi Di Caro

SP� 2314� 2nd Floor, East Neighbors Help: Bilingual Unsupervised WSD Using Context Sudha Bhingardive, Samiulla Shaikh and Pushpak Bhattacharyya

SP� 2406� 2nd Floor, East Reducing Annotation Effort for Quality Estimation via Active Learning Daniel Beck, Lucia Specia and Trevor Cohn

SP� 2461� 2nd Floor, East Ensemble Reranking with Linguistic and Semantic Features for Arabic Character Recognition Nadi Tomeh, Nizar Habash, Ryan Roth, Noura Farra, Pradeep Dasigi and Mona Diab

LP� 132� 2nd Floor, East A User-centric Model of Voting Intention from Social Media Vasileios Lampos, Daniel Preotiuc-Pietro and Trevor Cohn

�� Summarization and Generation → 3rd Floor, East

SP� 2047� 3rd Floor, East Evolutionary Hierarchical Dirichlet Process for Timeline Summarization Jiwei Li and Sujian Li

SP� 2189� 3rd Floor, East Using Integer Linear Programming in Concept-to-Text Generation to Produce More Compact Texts Gerasimos Lampouras and Ion Androutsopoulos

POSTER SESSIONS B

40

SP� 2509� 3rd Floor, East Sequential Summarization: A New Application for Timely Updated Twitter Trending Topics Dehong Gao, Wenjie Li and Renxian Zhang

SP� 2533� 3rd Floor, East A System for Summarizing Scientific Topics Starting from Keywords Rahul Jha, Amjad Abu-Jbara and Dragomir Radev

LP� 481� 3rd Floor, East Using Supervised Bigram-based ILP for Extractive Summarization Chen Li, Xian Qian and Yang Liu

LP� 505� 3rd Floor, East Summarization Through Submodularity and Dispersion Anirban Dasgupta, Ravi Kumar and Sujith Ravi

LP� 510� 3rd Floor, East Subtree Extractive Summarization via Submodular Maximization Hajime Morita, Ryohei Sasano, Hiroya Takamura and Manabu Okumura� �

� Syntax and Parsing → 2nd Floor, West

SP� 2181� 2nd Floor, West A Unified Morpho-Syntactic Scheme of Stanford Dependencies Reut Tsarfaty

SP� 2294� 2nd Floor, West Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain data Xuezhe Ma and Fei Xia

SP� 2300� 2nd Floor, West Iterative Transformation of Annotation Guidelines for Constituency Parsing Xiang Li, Wenbin Jiang, Yajuan Lv and Qun Liu

SP� 2389� 2nd Floor, West Nonparametric Bayesian Inference and Cubic-time Parsing for Tree-adjoining Grammars Elif Yamangil

SP� 2403� 2nd Floor, West Using CCG categories to improve Hindi dependency parsing Bharat Ram Ambati, Tejaswini Deoskar and Mark Steedman

SP� 2433 The Effect of Higher-Order Dependency Features in Discriminative Phrase-Structure Parsing Greg Coppola and Mark Steedman

41

SP� 2382� 2nd Floor, West Efficient Third-Order Non-Projective Dependency Parsers Andre Martins, Miguel Almeida and Noah A. Smith

SP� 2502� 2nd Floor, West A Lattice-based Framework for Joint Chinese Word Segmentation, POS Tagging and Parsing Zhiguo Wang, Chengqing Zong and Nianwen Xue

SP� 2558� 2nd Floor, West Efficient Implementation of Beam-Search Incremental Parsers Yoav Goldberg, Kai Zhao and Liang Huang

LP� 513� 2nd Floor, West The Effect of Non-tightness on Bayesian Estimation of PCFGs Shay B. Cohen and Mark Johnson

LP� 654� 2nd Floor, West Integrating Multiple Dependency Corpora for Inducing Wide-coverage Japanese CCG Resources Sumire Uematsu, Takuya Matsuzaki, Hiroki Hanaoka, Yusuke Miyao and Hideki Mima

LP� 658� 2nd Floor, West Transition-based Dependency Parsing with Selectional Branching Jinho D. Choi and Andrew McCallum

LP� 204� 2nd Floor, West Bilingually-Guided Monolingual Dependency Grammar Induction Kai Liu, Yajuan Lv, Wenbin Jiang and Qun Liu� �

� TACL → 2nd Floor, East

LP� 106� 2nd Floor, East Incremental Tree Substitution Grammar for Parsing and Word Prediction Federico Sangati, Frank Keller

LP� 80� 2nd Floor, East A Novel Feature-based Bayesian Model for Query Focused Multi-document Summarization Jiwei Li, Sujian Li, Claire Cardie

LP� 54� 2nd Floor, East Dijkstra-WSA: A Graph-based Approach to Word Sense Alignment Michael Matuschek, Iryna Gurevych

LP� 50� 2nd Floor, East Modeling Child Divergences from Adult Grammar with Automatic Error Correction Sam Sahakian, Benjamin Snyder� �

POSTER SESSIONS B

42

Tagging and Chunking → 3rd Floor East

SP� 2098� 3rd Floor East Part-of-speech Tagging with Antagonistic Adversaries Anders Søgaard

SP� 2090� 3rd Floor East Simpler Unsupervised POS Tagging with Bilingual Projections Long Thanh Duong, Paul Cook, Steven Bird and Pavel Pecina

LP� 465� 3rd Floor East Joint Word Alignment and Bilingual Named Entity Recognition Using Dual Decomposition Mengqiu Wang, Wanxiang Che and Christopher D. Manning

LP� 57� 3rd Floor East Resolving Entity Morphs in Censored Data Hongzhao Huang, Zhen Wen, Dian Yu, Heng Ji, Yizhou Sun, Jiawei Han and He Li� �

� Text Mining and Information Extraction → 2nd Floor, East

SP� 2002� 2nd Floor, East Temporal Signals Help Label Temporal Relations Leon Derczynski and Robert Gaizauskas

SP� 2095� 2nd Floor, East Diverse Keyword Extraction from Conversations Maryam Habibi and Andrei Popescu-Belis

SP� 2212� 2nd Floor, East Understanding Tables in Context using Standard NLP Toolkits Vidhya Govindaraju, Ce Zhang and Christopher Ré

SP� 2496� 2nd Floor, East Relation Extraction with Distant Supervision from Incomplete Knowledge Bases Wei Xu, Raphael Hoffmann, Ralph Grishman and Le Zhao

SP� 2544� 2nd Floor, East Joint Apposition Extraction with Syntactic and Semantic Constraints Will Radford and James R. Curran

LP� 647� 2nd Floor, East Learning to Extract International Relations from Political Context Brendan O'Connor, Brandon Stewart and Noah A. Smith

43

SP� 2382� 2nd Floor, West Efficient Third-Order Non-Projective Dependency Parsers Andre Martins, Miguel Almeida and Noah A. Smith

SP� 2502� 2nd Floor, West A Lattice-based Framework for Joint Chinese Word Segmentation, POS Tagging and Parsing Zhiguo Wang, Chengqing Zong and Nianwen Xue

SP� 2558� 2nd Floor, West Efficient Implementation of Beam-Search Incremental Parsers Yoav Goldberg, Kai Zhao and Liang Huang

LP� 513� 2nd Floor, West The Effect of Non-tightness on Bayesian Estimation of PCFGs Shay B. Cohen and Mark Johnson

LP� 654� 2nd Floor, West Integrating Multiple Dependency Corpora for Inducing Wide-coverage Japanese CCG Resources Sumire Uematsu, Takuya Matsuzaki, Hiroki Hanaoka, Yusuke Miyao and Hideki Mima

LP� 658� 2nd Floor, West Transition-based Dependency Parsing with Selectional Branching Jinho D. Choi and Andrew McCallum

LP� 204� 2nd Floor, West Bilingually-Guided Monolingual Dependency Grammar Induction Kai Liu, Yajuan Lv, Wenbin Jiang and Qun Liu� �

� TACL → 2nd Floor, East

LP� 106� 2nd Floor, East Incremental Tree Substitution Grammar for Parsing and Word Prediction Federico Sangati, Frank Keller

LP� 80� 2nd Floor, East A Novel Feature-based Bayesian Model for Query Focused Multi-document Summarization Jiwei Li, Sujian Li, Claire Cardie

LP� 54� 2nd Floor, East Dijkstra-WSA: A Graph-based Approach to Word Sense Alignment Michael Matuschek, Iryna Gurevych

LP� 50� 2nd Floor, East Modeling Child Divergences from Adult Grammar with Automatic Error Correction Sam Sahakian, Benjamin Snyder� �

POSTER SESSIONS B

42

Tagging and Chunking → 3rd Floor East

SP� 2098� 3rd Floor East Part-of-speech Tagging with Antagonistic Adversaries Anders Søgaard

SP� 2090� 3rd Floor East Simpler Unsupervised POS Tagging with Bilingual Projections Long Thanh Duong, Paul Cook, Steven Bird and Pavel Pecina

LP� 465� 3rd Floor East Joint Word Alignment and Bilingual Named Entity Recognition Using Dual Decomposition Mengqiu Wang, Wanxiang Che and Christopher D. Manning

LP� 57� 3rd Floor East Resolving Entity Morphs in Censored Data Hongzhao Huang, Zhen Wen, Dian Yu, Heng Ji, Yizhou Sun, Jiawei Han and He Li� �

� Text Mining and Information Extraction → 2nd Floor, East

SP� 2002� 2nd Floor, East Temporal Signals Help Label Temporal Relations Leon Derczynski and Robert Gaizauskas

SP� 2095� 2nd Floor, East Diverse Keyword Extraction from Conversations Maryam Habibi and Andrei Popescu-Belis

SP� 2212� 2nd Floor, East Understanding Tables in Context using Standard NLP Toolkits Vidhya Govindaraju, Ce Zhang and Christopher Ré

SP� 2496� 2nd Floor, East Relation Extraction with Distant Supervision from Incomplete Knowledge Bases Wei Xu, Raphael Hoffmann, Ralph Grishman and Le Zhao

SP� 2544� 2nd Floor, East Joint Apposition Extraction with Syntactic and Semantic Constraints Will Radford and James R. Curran

LP� 647� 2nd Floor, East Learning to Extract International Relations from Political Context Brendan O'Connor, Brandon Stewart and Noah A. Smith

43

STUDENT RESEARCH WORKSHOP – POSTER SESSION A:

th ndAugust 5 , 18.30 – 19.45, 2 Floor

SRW A1 2nd Floor, North Simple, Readable Sub-sentences Sigrid Klerke and Anders Søgaard

SRW A2 2nd Floor, North Exploring Word Order Universals: a Probabilistic Graphical Model Approach Xia Lu

SRW A3 2nd Floor, North Addressing Ambiguity in Unsupervised Part-of-Speech Induction with Substitute Vectors Volkan Cirik

SRW A4 2nd Floor, North A New Syntactic Metric for Evaluation of Machine Translation Melania Duma, Cristina Vertan and Wolfgang Menzel

SRW A5 2nd Floor, North High-quality Training Data Selection Using Latent Topics for Graph-based Semi-supervised Learning Akiko Eriguchi and Ichiro Kobayashi

SRW A6 2nd Floor, North A Comparison of Techniques to Automatically Identify Complex Words Matthew Shardlow

SRW A7 2nd Floor, North Detecting Chronic Critics Based on Sentiment Polarity and User's Behavior in Social Media Sho Takase, Akiko Murakami, Miki Enoki, Naoaki Okazaki and Kentaro Inui

SRW A8 2nd Floor, North Computational Considerations of Comparisons and Similes Vlad Niculae and Victoria Yaneva

SRW A9 2nd Floor, North Psycholinguistically Motivated Computational Models on the Organization and Processing of Morphologically Complex Words Tirthankar Dasgupta

SRW A10 2nd Floor, North Multigraph Clustering for Unsupervised Coreference Resolution Sebastian Martschat

SRW A11 2nd Floor, North Question Analysis for Polish Question Answering Piotr Przybyła

44

THE SRW POSTERS ARE BEING PRESENTED WITH THE SUPPORT OF THE QATAR COMPUTING RESEARCH INSTITUTE

STUDENT RESEARCH WORKSHOP – POSTER SESSION B:


SRW� B1� 2nd Floor, North Categorization of Turkish News Documents with Morphological Analysis Burak Kerim Akkuş and Ruket Cakici

SRW� B2� 2nd Floor, North Crawling Microblogging Services to Gather Language-classified URLs. Workflow and Case Study Adrien Barbaresi

SRW� B3� 2nd Floor, North Patient Experience in Online Support Forums: Modeling Interpersonal Interactions and Medication Use Annie Chen

SRW� B4� 2nd Floor, North Detecting Metaphor by Contextual Analogy Eirini Florou

SRW� B5� 2nd Floor, North Survey on Parsing Three Dependency Representations for English Angelina Ivanova, Stephan Oepen and Lilja Øvrelid

SRW� B6� 2nd Floor, North What Causes a Causal Relation? Detecting Causal Triggers in Biomedical Scientific Discourse Claudiu Mihăilă and Sophia Ananiadou�

SRW� B7� 2nd Floor, North Text Classification Based on the Latent Topics of Important Sentences extracted by the PageRank Algorithm Yukari Ogura and Ichiro Kobayashi

SRW� B8� 2nd Floor, North Automated Collocation Suggestion for Japanese Second Language Learners Lis Pereira, Erlyn Manguilimotan and Yuji Matsumoto

SRW� B9� 2nd Floor, North Understanding Verbs Based on Overlapping Verbs Senses Kavitha Rajan

SRW� B10� 2nd Floor, North Topic Modeling based Classification of Clinical Reports Efsun Sarioglu, Kabir Yadav and Hyeong-Ah Choi

SRW� B11� 2nd Floor, North Annotating Named Entities in Clinical Text by Combining Pre-annotation and Active Learning Maria Skeppstedt

45

STUDENT RESEARCH WORKSHOP – POSTER SESSION A:


SRW A1 2nd Floor, North Simple, Readable Sub-sentences Sigrid Klerke and Anders Søgaard

SRW A2 2nd Floor, North Exploring Word Order Universals: a Probabilistic Graphical Model Approach Xia Lu

SRW A3 2nd Floor, North Addressing Ambiguity in Unsupervised Part-of-Speech Induction with Substitute Vectors Volkan Cirik

SRW A4 2nd Floor, North A New Syntactic Metric for Evaluation of Machine Translation Melania Duma, Cristina Vertan and Wolfgang Menzel

SRW A5 2nd Floor, North High-quality Training Data Selection Using Latent Topics for Graph-based Semi-supervised Learning Akiko Eriguchi and Ichiro Kobayashi

SRW A6 2nd Floor, North A Comparison of Techniques to Automatically Identify Complex Words Matthew Shardlow

SRW A7 2nd Floor, North Detecting Chronic Critics Based on Sentiment Polarity and User's Behavior in Social Media Sho Takase, Akiko Murakami, Miki Enoki, Naoaki Okazaki and Kentaro Inui

SRW A8 2nd Floor, North Computational Considerations of Comparisons and Similes Vlad Niculae and Victoria Yaneva

SRW A9 2nd Floor, North Psycholinguistically Motivated Computational Models on the Organization and Processing of Morphologically Complex Words Tirthankar Dasgupta

SRW A10 2nd Floor, North Multigraph Clustering for Unsupervised Coreference Resolution Sebastian Martschat

SRW A11 2nd Floor, North Question Analysis for Polish Question Answering Piotr Przybyła

44

THE SRW POSTERS ARE BEING PRESENTED WITH THE SUPPORT OF THE QATAR COMPUTING RESEARCH INSTITUTE

STUDENT RESEARCH WORKSHOP – POSTER SESSION B:


SRW� B1� 2nd Floor, North Categorization of Turkish News Documents with Morphological Analysis Burak Kerim Akkuş and Ruket Cakici

SRW� B2� 2nd Floor, North Crawling Microblogging Services to Gather Language-classified URLs. Workflow and Case Study Adrien Barbaresi

SRW� B3� 2nd Floor, North Patient Experience in Online Support Forums: Modeling Interpersonal Interactions and Medication Use Annie Chen

SRW� B4� 2nd Floor, North Detecting Metaphor by Contextual Analogy Eirini Florou

SRW� B5� 2nd Floor, North Survey on Parsing Three Dependency Representations for English Angelina Ivanova, Stephan Oepen and Lilja Øvrelid

SRW� B6� 2nd Floor, North What Causes a Causal Relation? Detecting Causal Triggers in Biomedical Scientific Discourse Claudiu Mihăilă and Sophia Ananiadou�

SRW� B7� 2nd Floor, North Text Classification Based on the Latent Topics of Important Sentences extracted by the PageRank Algorithm Yukari Ogura and Ichiro Kobayashi

SRW� B8� 2nd Floor, North Automated Collocation Suggestion for Japanese Second Language Learners Lis Pereira, Erlyn Manguilimotan and Yuji Matsumoto

SRW� B9� 2nd Floor, North Understanding Verbs Based on Overlapping Verbs Senses Kavitha Rajan

SRW� B10� 2nd Floor, North Topic Modeling based Classification of Clinical Reports Efsun Sarioglu, Kabir Yadav and Hyeong-Ah Choi

SRW� B11� 2nd Floor, North Annotating Named Entities in Clinical Text by Combining Pre-annotation and Active Learning Maria Skeppstedt

45

SYSTEM DEMONSTRATIONS

th rdSESSION A: August 5 , 18.30 – 19.45, 3 Floor

SD� A1� 3rd Floor, North WEBANNO: A FLEXIBLE, WEB-BASED AND VISUALLY SUPPORTED SYSTEM FOR DISTRIBUTED ANNOTATIONS Seid Muhie Yimam, Iryna Gurevych, Richard Eckart de Castilho and Chris Biemann�SD� A23� 3rd Floor, North A STACKING-BASED APPROACH TO TWITTER USER GEOLOCATION PREDICTION Bo Han, Paul Cook and Timothy Baldwin�SD� A3� 3rd Floor, North AN OPEN SOURCE TOOLKIT FOR QUANTITATIVE HISTORICAL LINGUISTICS Johann-Mattis List and Steven Moran�SD� A4� 3rd Floor, North ANNOMARKET: AN OPEN CLOUD PLATFORM FOR NLP Valentin Tablan, Kalina Bontcheva, Ian Roberts, Hamish Cunningham and Marin Dimitrov�SD� A5� 3rd Floor, North TRAVATAR: A FOREST-TO-STRING MACHINE TRANSLATION ENGINE BASED ON TREE TRANSDUCERS Graham Neubig�SD� A6� 3rd Floor, North DETECTING EVENT-RELATED LINKS AND SENTIMENTS FROM SOCIAL MEDIA TEXTS Alexandra Balahur and Hristo Tanev�SD� A7� 3rd Floor, North SORT: AN INTERACTIVE SOURCE-REWRITING TOOL FOR IMPROVED TRANSLATION Shachar Mirkin, Sriram Venkatapathy, Marc Dymetman and Ioan Calapodescu�SD� A8� 3rd Floor, North DISSECT - DISTRIBUTIONAL SEMANTICS COMPOSITION TOOLKIT Georgiana Dinu, Nghia The Pham and Marco Baroni�SD� A9� 3rd Floor, North QUEST - A TRANSLATION QUALITY ESTIMATION FRAMEWORK Lucia Specia, Kashif Shah, Jose Guilherme Camargo de Souza and Trevor Cohn�SD� A10� 3rd Floor, North DKPRO WSD: A GENERALIZED UIMA-BASED FRAMEWORK FOR WORD SENSE DISAMBIGUATION Tristan Miller, Nicolai Erbs, Hans-Peter Zorn, Torsten Zesch and Iryna Gurevych�SD� A11� 3rd Floor, North PLIS: A PROBABILISTIC LEXICAL INFERENCE SYSTEM Eyal Shnarch, Erel Segal-haLevi, Jacob Goldberger and Ido Dagan�


46

SD� A12� 3rd Floor, North EXTENDING AN INTEROPERABLE PLATFORM TO FACILITATE THE CREATION OF MULTILINGUAL AND MULTIMODAL NLP APPLICATIONS Georgios Kontonatsios, Paul Thompson, Riza Theresa Batista-Navarro, Claudiu Mihăilă, Ioannis Korkontzelos and Sophia Ananiadou�SD� A13� 3rd Floor, North PHONMATRIX: VISUALIZING CO-OCCURRENCE CONSTRAINTS OF SOUNDS Thomas Mayer and Christian Rohrdantz�SD� A14� 3rd Floor, North FUDANNLP: A TOOLKIT FOR CHINESE NATURAL LANGUAGE PROCESSING Xipeng Qiu, Qi Zhang and Xuanjing Huang�SD� A15� 3rd Floor, North PAL: A CHATTERBOT SYSTEM FOR ANSWERING DOMAIN-SPECIFIC QUESTIONS Yuanchao Liu, Ming Liu, Xiaolong Wang and Jingjing Li�SD� A16� 3rd Floor, North ICARUS – AN EXTENSIBLE GRAPHICAL SEARCH TOOL FOR DEPENDENCY TREEBANKS Markus Gärtner, Gregor Thiele, Wolfgang Seeker, Anders Björkelund and Jonas Kuhn�SD� A17� 3rd Floor, North MEET EDGAR, A TUTORING AGENT AT MONSERRATE Pedro Fialho, Luísa Coheur, Sérgio Curto, Pedro Cláudio, Ângela Costa, Alberto Abad, Hugo Meinedo and Isabel Trancoso

47


th rdSESSION A: August 5 , 18.30 – 19.45, 3 Floor

SD� A1� 3rd Floor, North WEBANNO: A FLEXIBLE, WEB-BASED AND VISUALLY SUPPORTED SYSTEM FOR DISTRIBUTED ANNOTATIONS Seid Muhie Yimam, Iryna Gurevych, Richard Eckart de Castilho and Chris Biemann�SD� A23� 3rd Floor, North A STACKING-BASED APPROACH TO TWITTER USER GEOLOCATION PREDICTION Bo Han, Paul Cook and Timothy Baldwin�SD� A3� 3rd Floor, North AN OPEN SOURCE TOOLKIT FOR QUANTITATIVE HISTORICAL LINGUISTICS Johann-Mattis List and Steven Moran�SD� A4� 3rd Floor, North ANNOMARKET: AN OPEN CLOUD PLATFORM FOR NLP Valentin Tablan, Kalina Bontcheva, Ian Roberts, Hamish Cunningham and Marin Dimitrov�SD� A5� 3rd Floor, North TRAVATAR: A FOREST-TO-STRING MACHINE TRANSLATION ENGINE BASED ON TREE TRANSDUCERS Graham Neubig�SD� A6� 3rd Floor, North DETECTING EVENT-RELATED LINKS AND SENTIMENTS FROM SOCIAL MEDIA TEXTS Alexandra Balahur and Hristo Tanev�SD� A7� 3rd Floor, North SORT: AN INTERACTIVE SOURCE-REWRITING TOOL FOR IMPROVED TRANSLATION Shachar Mirkin, Sriram Venkatapathy, Marc Dymetman and Ioan Calapodescu�SD� A8� 3rd Floor, North DISSECT - DISTRIBUTIONAL SEMANTICS COMPOSITION TOOLKIT Georgiana Dinu, Nghia The Pham and Marco Baroni�SD� A9� 3rd Floor, North QUEST - A TRANSLATION QUALITY ESTIMATION FRAMEWORK Lucia Specia, Kashif Shah, Jose Guilherme Camargo de Souza and Trevor Cohn�SD� A10� 3rd Floor, North DKPRO WSD: A GENERALIZED UIMA-BASED FRAMEWORK FOR WORD SENSE DISAMBIGUATION Tristan Miller, Nicolai Erbs, Hans-Peter Zorn, Torsten Zesch and Iryna Gurevych�SD� A11� 3rd Floor, North PLIS: A PROBABILISTIC LEXICAL INFERENCE SYSTEM Eyal Shnarch, Erel Segal-haLevi, Jacob Goldberger and Ido Dagan�


46

SD� A12� 3rd Floor, North EXTENDING AN INTEROPERABLE PLATFORM TO FACILITATE THE CREATION OF MULTILINGUAL AND MULTIMODAL NLP APPLICATIONS Georgios Kontonatsios, Paul Thompson, Riza Theresa Batista-Navarro, Claudiu Mihăilă, Ioannis Korkontzelos and Sophia Ananiadou�SD� A13� 3rd Floor, North PHONMATRIX: VISUALIZING CO-OCCURRENCE CONSTRAINTS OF SOUNDS Thomas Mayer and Christian Rohrdantz�SD� A14� 3rd Floor, North FUDANNLP: A TOOLKIT FOR CHINESE NATURAL LANGUAGE PROCESSING Xipeng Qiu, Qi Zhang and Xuanjing Huang�SD� A15� 3rd Floor, North PAL: A CHATTERBOT SYSTEM FOR ANSWERING DOMAIN-SPECIFIC QUESTIONS Yuanchao Liu, Ming Liu, Xiaolong Wang and Jingjing Li�SD� A16� 3rd Floor, North ICARUS – AN EXTENSIBLE GRAPHICAL SEARCH TOOL FOR DEPENDENCY TREEBANKS Markus Gärtner, Gregor Thiele, Wolfgang Seeker, Anders Björkelund and Jonas Kuhn�SD� A17� 3rd Floor, North MEET EDGAR, A TUTORING AGENT AT MONSERRATE Pedro Fialho, Luísa Coheur, Sérgio Curto, Pedro Cláudio, Ângela Costa, Alberto Abad, Hugo Meinedo and Isabel Trancoso

47

48

th rdSESSION B: August 5 , 19.45 – 21.00, 3 Floor

SD� B1� 3rd Floor, North LINGGLE: A WEB-SCALE LINGUISTIC SEARCH ENGINE FOR WORDS IN CONTEXT Joanne Boisson, Ting-Hui Kao, Jian-Cheng Wu, Tzu-Hsi Yen and Jason S. Chang

SD� B2 3rd Floor, North MR. MIRA: OPEN-SOURCE LARGE-MARGIN STRUCTURED LEARNING ON MAPREDUCE Vladimir Eidelman, Ke Wu, Ferhan Ture, Philip Resnik and Jimmy Lin

SD� B3� 3rd Floor, North PARAQUERY: MAKING SENSE OF PARAPHRASE COLLECTIONS Lili Kotlerman, Nitin Madnani and Aoife Cahill�SD� B4� 3rd Floor, North HYENA-LIVE: FINE-GRAINED ONLINE ENTITY TYPE CLASSIFICATION FROM NATURAL-LANGUAGE TEXT Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart, Marc Spaniol and Gerhard Weikum �SD� B5� 3rd Floor, North PATHS: A SYSTEM FOR ACCESSING CULTURAL HERITAGE COLLECTIONS Eneko Agirre, Nikolaos Aletras, Paul Clough, Samuel Fernando, Paula Goodale, Mark Hall, Aitor Soroa and Mark Stevenson

SD B6� 3rd Floor, North FLUID CONSTRUCTION GRAMMAR FOR HISTORICAL AND EVOLUTIONARY LINGUISTICS Pieter Wellens, Remi van Trijp, Katrien Beuls and Luc Steels�SD� B7� 3rd Floor, North PROPMINER: A WORKFLOW FOR INTERACTIVE INFORMATION EXTRACTION AND EXPLORATION USING DEPENDENCY TREES Alan Akbik, Oresti Konomi and Michail Melnikov�SD� B8� 3rd Floor, North DOCENT: A DOCUMENT-LEVEL DECODER FOR PHRASE-BASED STATISTICAL MACHINE TRANSLATION Christian Hardmeier, Sara Stymne, Jörg Tiedemann and Joakim Nivre�SD� B9� 3rd Floor, North SEMILAR: THE SEMANTIC SIMILARITY TOOLKIT Vasile Rus, Nobal Niraula, Rajendra Banjade, Dan Stefanescu and Mihai Lintean

SD� B10� 3rd Floor, North DKPRO SIMILARITY: AN OPEN SOURCE FRAMEWORK FOR TEXT SIMILARITY Daniel Bär, Torsten Zesch and Iryna Gurevych�SD� B11� 3rd Floor, North TAG2BLOG: NARRATIVE GENERATION FROM SATELLITE TAG DATA Kapila Ponnamperuma, Advaith Siddharthan, Cheng Zeng, Chris Mellish and René van der Wal�


49

SD� B12� 3rd Floor, North DEVELOPMENT AND ANALYSIS OF NLP PIPELINES IN ARGO Rafal Rak, Andrew Rowley, Jacob Carter and Sophia Ananiadou�SD� B13� 3rd Floor, North TRANSDOOP: A MAP-REDUCE BASED CROWDSOURCED TRANSLATION FOR COMPLEX DOMAIN Anoop Kunchukuttan, Rajen Chatterjee, Shourya Roy, Abhijit Mishra and Pushpak Bhattacharyya �SD� B14� 3rd Floor, North TSEARCH: FLEXIBLE AND FAST SEARCH OVER AUTOMATIC TRANSLATIONS FOR IMPROVED QUALITY/ERROR ANALYSIS Meritxell Gonzàlez, Laura Mascarell and Lluís Màrquez �SD� B15� 3rd Floor, North A VISUAL ANALYTICS SYSTEM FOR CLUSTER EXPLORATION Andreas Lamprecht, Annette Hautli, Christian Rohrdantz and Tina Bögel�SD� B16� 3rd Floor, North VSEM: AN OPEN LIBRARY FOR VISUAL SEMANTICS REPRESENTATION Elia Bruni, Ulisse Bordignon, Jasper Uijlings, Adam Liska and Irina Sergienya�SD� B17� 3rd Floor, North A JAVA FRAMEWORK FOR MULTILINGUAL DEFINITION AND HYPERNYM EXTRACTION Stefano Faralli and Roberto Navigli

48

th rdSESSION B: August 5 , 19.45 – 21.00, 3 Floor

SD� B1� 3rd Floor, North LINGGLE: A WEB-SCALE LINGUISTIC SEARCH ENGINE FOR WORDS IN CONTEXT Joanne Boisson, Ting-Hui Kao, Jian-Cheng Wu, Tzu-Hsi Yen and Jason S. Chang

SD� B2 3rd Floor, North MR. MIRA: OPEN-SOURCE LARGE-MARGIN STRUCTURED LEARNING ON MAPREDUCE Vladimir Eidelman, Ke Wu, Ferhan Ture, Philip Resnik and Jimmy Lin

SD� B3� 3rd Floor, North PARAQUERY: MAKING SENSE OF PARAPHRASE COLLECTIONS Lili Kotlerman, Nitin Madnani and Aoife Cahill�SD� B4� 3rd Floor, North HYENA-LIVE: FINE-GRAINED ONLINE ENTITY TYPE CLASSIFICATION FROM NATURAL-LANGUAGE TEXT Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart, Marc Spaniol and Gerhard Weikum �SD� B5� 3rd Floor, North PATHS: A SYSTEM FOR ACCESSING CULTURAL HERITAGE COLLECTIONS Eneko Agirre, Nikolaos Aletras, Paul Clough, Samuel Fernando, Paula Goodale, Mark Hall, Aitor Soroa and Mark Stevenson

SD B6� 3rd Floor, North FLUID CONSTRUCTION GRAMMAR FOR HISTORICAL AND EVOLUTIONARY LINGUISTICS Pieter Wellens, Remi van Trijp, Katrien Beuls and Luc Steels�SD� B7� 3rd Floor, North PROPMINER: A WORKFLOW FOR INTERACTIVE INFORMATION EXTRACTION AND EXPLORATION USING DEPENDENCY TREES Alan Akbik, Oresti Konomi and Michail Melnikov�SD� B8� 3rd Floor, North DOCENT: A DOCUMENT-LEVEL DECODER FOR PHRASE-BASED STATISTICAL MACHINE TRANSLATION Christian Hardmeier, Sara Stymne, Jörg Tiedemann and Joakim Nivre�SD� B9� 3rd Floor, North SEMILAR: THE SEMANTIC SIMILARITY TOOLKIT Vasile Rus, Nobal Niraula, Rajendra Banjade, Dan Stefanescu and Mihai Lintean

SD� B10� 3rd Floor, North DKPRO SIMILARITY: AN OPEN SOURCE FRAMEWORK FOR TEXT SIMILARITY Daniel Bär, Torsten Zesch and Iryna Gurevych�SD� B11� 3rd Floor, North TAG2BLOG: NARRATIVE GENERATION FROM SATELLITE TAG DATA Kapila Ponnamperuma, Advaith Siddharthan, Cheng Zeng, Chris Mellish and René van der Wal�


49

SD� B12� 3rd Floor, North DEVELOPMENT AND ANALYSIS OF NLP PIPELINES IN ARGO Rafal Rak, Andrew Rowley, Jacob Carter and Sophia Ananiadou�SD� B13� 3rd Floor, North TRANSDOOP: A MAP-REDUCE BASED CROWDSOURCED TRANSLATION FOR COMPLEX DOMAIN Anoop Kunchukuttan, Rajen Chatterjee, Shourya Roy, Abhijit Mishra and Pushpak Bhattacharyya �SD� B14� 3rd Floor, North TSEARCH: FLEXIBLE AND FAST SEARCH OVER AUTOMATIC TRANSLATIONS FOR IMPROVED QUALITY/ERROR ANALYSIS Meritxell Gonzàlez, Laura Mascarell and Lluís Màrquez �SD� B15� 3rd Floor, North A VISUAL ANALYTICS SYSTEM FOR CLUSTER EXPLORATION Andreas Lamprecht, Annette Hautli, Christian Rohrdantz and Tina Bögel�SD� B16� 3rd Floor, North VSEM: AN OPEN LIBRARY FOR VISUAL SEMANTICS REPRESENTATION Elia Bruni, Ulisse Bordignon, Jasper Uijlings, Adam Liska and Irina Sergienya�SD� B17� 3rd Floor, North A JAVA FRAMEWORK FOR MULTILINGUAL DEFINITION AND HYPERNYM EXTRACTION Stefano Faralli and Roberto Navigli


th Main Conference: Tue, August 6

Overview8.00 – 18.00 Registration Floor 0

9.00 – 10.00 Industrial Lecture: Facebook Hall 3

10.00 – 10.30 Best Paper Award Hall 3



12.15 – 13.45 Lunch Break



16.15 – 16.45 Coffee Break


18.30 Banquet Sheraton Hotel

Industrial Lecture: Lars Rasmussen (Facebook)The Natural Language Interface of Graph Search

thTuesday, August 6 , 2013, 9.00 am – 10.00 am Hall 3→Short Bio: Lars Rasmussen graduated from the University of Aarhus with a degree in Computer Science and Mathematics. He gained his MSc in Computer Systems Engineering from the University of Edinburgh in 1992. Mr. Rasmussen began his PhD in the Laboratory for Foundations of Computer Science at Edinburgh, later to move to Berkeley, California, USA. He received his PhD from the University of California, Berkeley in 1998. He is a co-founder of Where 2 Technologies, a mapping-related start-up in Sydney, Australia. The company was bought by Google in 2004, to create the popular, free, browser-based software, Google Maps. Mr. Rasmussen was subsequently employed by Google in the engineering team at the company's Australian office in Sydney. He became one of the originators of the Google Wave project. Rasmussen left Google and joined Facebook where he has worked, among other things, as engineering director for the Facebook Graph Search project. In 2010, he was awarded the Pearcey Award for NSW ICT Entrepreneurs of the Year.



9.00 Industrial Lecture: Hall 3

Facebook

10.00 Best Paper Award: Hall 3

10.30 Coffee Break


Machine NLP Semantics IV Language Summarization

Translation: Applications I Resources I & Generation I

Statistical

Models IV

12.15 Lunch Break


Machine NLP Cognitive Language Summarization

Translation: Applications II Modeling & Resources II & Generation II

Statistical Psycholinguistics� Machine

Models V Lexical Semantics�& Translation:

Ontologies Methods

15:00 Papers LP 7a LP 7b LP 7c LP 7d LP 7e

Machine NLP Text Mining & Cognitive Summarization

Translation: Applications III Information Modeling & & Generation III

Methods, Extraction Psycholinguistics

Applications & Phonology &

Evaluations I Morphology

16.15 Coffee Break

16.45 Papers SP 8a SP 8b SP 8c SP 8d SRW Machine NLP Lexical Semantics Evaluation

Translation: Applications & Ontologies Methods,

Methods, Information

Applications & Retrieval &

Evaluations Language

Resources

18.30 Banquet The Sheraton Hotel,

Royal Hall & Sredets Hall

thProgram – Tue, August 6

50 51


th Main Conference: Tue, August 6


9.00 – 10.00 Industrial Lecture: Facebook Hall 3

10.00 – 10.30 Best Paper Award Hall 3








18.30 Banquet Sheraton Hotel

Industrial Lecture: Lars Rasmussen (Facebook)The Natural Language Interface of Graph Search

thTuesday, August 6 , 2013, 9.00 am – 10.00 am Hall 3→Short Bio: Lars Rasmussen graduated from the University of Aarhus with a degree in Computer Science and Mathematics. He gained his MSc in Computer Systems Engineering from the University of Edinburgh in 1992. Mr. Rasmussen began his PhD in the Laboratory for Foundations of Computer Science at Edinburgh, later to move to Berkeley, California, USA. He received his PhD from the University of California, Berkeley in 1998. He is a co-founder of Where 2 Technologies, a mapping-related start-up in Sydney, Australia. The company was bought by Google in 2004, to create the popular, free, browser-based software, Google Maps. Mr. Rasmussen was subsequently employed by Google in the engineering team at the company's Australian office in Sydney. He became one of the originators of the Google Wave project. Rasmussen left Google and joined Facebook where he has worked, among other things, as engineering director for the Facebook Graph Search project. In 2010, he was awarded the Pearcey Award for NSW ICT Entrepreneurs of the Year.



9.00 Industrial Lecture: Hall 3

Facebook

10.00 Best Paper Award: Hall 3

10.30 Coffee Break


Machine NLP Semantics IV Language Summarization

Translation: Applications I Resources I & Generation I

Statistical

Models IV

12.15 Lunch Break


Machine NLP Cognitive Language Summarization

Translation: Applications II Modeling & Resources II & Generation II

Statistical Psycholinguistics� Machine

Models V Lexical Semantics�& Translation:

Ontologies Methods

15:00 Papers LP 7a LP 7b LP 7c LP 7d LP 7e

Machine NLP Text Mining & Cognitive Summarization

Translation: Applications III Information Modeling & & Generation III

Methods, Extraction Psycholinguistics

Applications & Phonology &

Evaluations I Morphology

16.15 Coffee Break

16.45 Papers SP 8a SP 8b SP 8c SP 8d SRW Machine NLP Lexical Semantics Evaluation

Translation: Applications & Ontologies Methods,

Methods, Information

Applications & Retrieval &

Evaluations Language

Resources

18.30 Banquet The Sheraton Hotel,

Royal Hall & Sredets Hall

thProgram – Tue, August 6

50 51


9.00 Industrial Lecture: Lars Rasmussen (Facebook) The Natural Language Interface of Graph Search Hall 3→

10.00 Best Paper Award Hall 3→


LONG PAPERS, SHORT PAPERS, STUDENT RESEARCH WORKSHOP


LONG PAPERS

LP 5a Machine Translation: Statistical Models IV → Hall 3 11.00 Graph Propagation for Paraphrasing Out-of-Vocabulary Words in Statistical Machine Translation Majid Razmara, Maryam Siahbani, Reza Haffari and Anoop Sarkar

11.25 Online Relative Margin Maximization for Statistical Machine Translation Vladimir Eidelman, Yuval Marton and Philip Resnik

11.50 Handling Ambiguities of Bilingual Predicate-Argument Structures for Statistical Machine Translation Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong

LP 5b NLP Applications I → Hall 6 11.00 Reconstructing an Indo-European Family Tree from Non-native English texts Ryo Nagata and Edward Whittaker

11.25 Word Association Profiles and their Use for Automated Scoring of Essays Beata Beigman Klebanov and Michael Flor

11.50 Adaptive Parser-Centric Text Normalization Congle Zhang, Tyler Baldwin, Howard Ho, Benny Kimelfeld and Yunyao Li

thExtended Daily Program – Tue, August 6


52

LP 5c Semantics IV → Hall 7 11.00 A Random Walk Approach to Selectional Preferences Based on Preference Ranking and Propagation Zhenhua Tian, Hengheng Xiang, Ziqi Liu and Qinghua Zheng

11.25 ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling Egoitz Laparra and German Rigau

11.50 Cross-lingual Transfer of Semantic Role Labeling Models Mikhail Kozhevnikov and Ivan Titov

LP 5d Language Resources I → Hall 8

11.00 DErivBase: Inducing and Evaluating a Derivational Morphology Resource for German Britta Zeller, Jan Snajder and Sebastian Pado

11.25 Crowdsourcing Interaction Logs to Understand Text Reuse from the Web Martin Potthast, Matthias Hagen, Michael Völske and Benno Stein

11.50 SPred: Large-scale Harvesting of Semantic Predicates Tiziano Flati and Roberto Navigli

LP 5e Summarization and Generation I → Hall 10 11.00 Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain Jackie Chi Kit Cheung and Gerald Penn

11.25 HEADY: News Headline Abstraction Through Event Pattern Clustering Enrique Alfonseca, Daniele Pighin and Guillermo Garrido

11.50 Conditional Random Fields for Responsive Surface Realisation using Global Features Nina Dethlefs, Helen Hastie, Heriberto Cuayahuitl and Oliver Lemon 12.15 Lunch Break

LP 6a Machine Translation: Statistical Models V → Hall 3

13.45 Two-Neighbor Orientation Model with Cross-Boundary Global Contexts Hendra Setiawan, Bowen Zhou, Bing Xiang and Libin Shen

14.10 Cut the noise: Mutually Reinforcing Reordering and Alignments for Improved Machine Translation Karthik Visweswariah, Mitesh M. Khapra and Ananthakrishnan Ramanathan

14.35 Vector Space Model for Adaptation in Statistical Machine Translation Boxing Chen, Roland Kuhn and George Foster

53


9.00 Industrial Lecture: Lars Rasmussen (Facebook) The Natural Language Interface of Graph Search Hall 3→

10.00 Best Paper Award Hall 3→


LONG PAPERS, SHORT PAPERS, STUDENT RESEARCH WORKSHOP


LONG PAPERS

LP 5a Machine Translation: Statistical Models IV → Hall 3 11.00 Graph Propagation for Paraphrasing Out-of-Vocabulary Words in Statistical Machine Translation Majid Razmara, Maryam Siahbani, Reza Haffari and Anoop Sarkar

11.25 Online Relative Margin Maximization for Statistical Machine Translation Vladimir Eidelman, Yuval Marton and Philip Resnik

11.50 Handling Ambiguities of Bilingual Predicate-Argument Structures for Statistical Machine Translation Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong

LP 5b NLP Applications I → Hall 6 11.00 Reconstructing an Indo-European Family Tree from Non-native English texts Ryo Nagata and Edward Whittaker

11.25 Word Association Profiles and their Use for Automated Scoring of Essays Beata Beigman Klebanov and Michael Flor

11.50 Adaptive Parser-Centric Text Normalization Congle Zhang, Tyler Baldwin, Howard Ho, Benny Kimelfeld and Yunyao Li

thExtended Daily Program – Tue, August 6


52

LP 5c Semantics IV → Hall 7 11.00 A Random Walk Approach to Selectional Preferences Based on Preference Ranking and Propagation Zhenhua Tian, Hengheng Xiang, Ziqi Liu and Qinghua Zheng

11.25 ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling Egoitz Laparra and German Rigau

11.50 Cross-lingual Transfer of Semantic Role Labeling Models Mikhail Kozhevnikov and Ivan Titov

LP 5d Language Resources I → Hall 8

11.00 DErivBase: Inducing and Evaluating a Derivational Morphology Resource for German Britta Zeller, Jan Snajder and Sebastian Pado

11.25 Crowdsourcing Interaction Logs to Understand Text Reuse from the Web Martin Potthast, Matthias Hagen, Michael Völske and Benno Stein

11.50 SPred: Large-scale Harvesting of Semantic Predicates Tiziano Flati and Roberto Navigli

LP 5e Summarization and Generation I → Hall 10 11.00 Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain Jackie Chi Kit Cheung and Gerald Penn

11.25 HEADY: News Headline Abstraction Through Event Pattern Clustering Enrique Alfonseca, Daniele Pighin and Guillermo Garrido

11.50 Conditional Random Fields for Responsive Surface Realisation using Global Features Nina Dethlefs, Helen Hastie, Heriberto Cuayahuitl and Oliver Lemon 12.15 Lunch Break

LP 6a Machine Translation: Statistical Models V → Hall 3

13.45 Two-Neighbor Orientation Model with Cross-Boundary Global Contexts Hendra Setiawan, Bowen Zhou, Bing Xiang and Libin Shen

14.10 Cut the noise: Mutually Reinforcing Reordering and Alignments for Improved Machine Translation Karthik Visweswariah, Mitesh M. Khapra and Ananthakrishnan Ramanathan

14.35 Vector Space Model for Adaptation in Statistical Machine Translation Boxing Chen, Roland Kuhn and George Foster

53

LP 6b NLP Applications II → Hall 6 13.45 From Natural Language Specifications to Program Input Parsers Tao Lei, Fan Long, Regina Barzilay and Martin Rinard

14.10 Entity Linking for Tweets Xiaohua Liu, Yitong Li, Haocheng Wu, Ming Zhou, Furu Wei And Yi Lu

14.35 Identification of Speakers in Novels Hua He, Denilson Barbosa and Grzegorz Kondrak LP 6c Cognitive Modelling and Psycholinguistics / Lexical Semantics and Ontologies → Hall 7

13.45 Language Acquisition and Probabilistic Models: Keeping it Simple Aline Villavicencio, Marco Idiart, Robert Berwick and Igor Malioutov

14.10 A Two Level Model for Context Sensitive Inference Rules Oren Melamud, Jonathan Berant, Ido Dagan, Jacob Goldberger and Idan Szpektor

14.35 Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity Mohammad Taher Pilehvar, David Jurgens and Roberto Navigli

LP 6d Language Resources II / Machine Translation: Methods → Hall 8 13.45 Linking and Extending an Open Multilingual Wordnet Francis Bond and Ryan Foster

14.10 FrameNet on the Way to Babel: Creating a Bilingual FrameNet Using Wiktionary as Interlingual Connection Silvana Hartmann and Iryna Gurevych

14.35 Dirt Cheap Web-Scale Parallel Text from the Common Crawl Jason Smith, Herve Saint-Amand, Magdalena Plamada, Philipp Koehn, Chris Callison-Burch and Adam Lopez

LP 6e Summarization and Generation II → Hall 10

13.45 A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization Lu Wang, Hema Raghavan, Vittorio Castelli, Radu Florian and Claire Cardie

14.10 Domain-Independent Abstract Generation for Focused Meeting Summarization Lu Wang and Claire Cardie

14.35 A Statistical NLG Framework for Aggregated Planning and Realization Ravi Kondadadi, Blake Howald and Frank Schilder


54

LP 7a Machine Translation: Methods, Applications and Evaluations I → Hall 3 15.00 Models of Translation Competitions Mark Hopkins and Jon May

15.25 Learning a Phrase-based Translation Model from Monolingual Data with Application to Domain Adaptation Jiajun Zhang and Chengqing Zong

15.50 SenseSpotting: Never Let Your Parallel Data Tie you to an Old Domain Marine Carpuat, Hal Daume III, Katie Henry, Ann Irvine, Jagadeesh Jagarlamudi and Rachel Rudinger

LP 7b NLP Applications III → Hall 6 15.00 BRAINSUP: Brainstorming Support for Creative Sentence Generation Gozde Ozbal, Daniele Pighin and Carlo Strapparava

15.25 Grammatical Error Correction Using Integer Linear Programming Yuanbin Wu and Hwee Tou Ng

15.50 Text-Driven Toponym Resolution using Indirect Supervision Michael Speriosu and Jason Baldridge

LP 7c Text Mining and Information Extraction → Hall 7 15.00 Argument Inference from Relevant Event Mentions in Chinese Argument Extraction Peifeng Li, Qiaoming Zhu and Guodong Zhou

15.25 Fine-grained Semantic Typing of Emerging Entities Ndapandula Nakashole, Tomasz Tylenda and Gerhard Weikum

15.50 Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction Barbara Plank and Alessandro Moschitti

LP 7d Cognitive Modelling and Psycholinguistics / Phonology and Morphology → Hall 8 15.00 A Joint Model of Word Segmentation and Phonological Variation for English Word-final /t/-deletion Benjamin Börschinger, Mark Johnson and Katherine Demuth

15.25 Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics Angeliki Lazaridou, Marco Marelli, Roberto Zamparelli and Marco Baroni

15.50 Unsupervised Consonant-Vowel Prediction over Hundreds of Languages Young-Bum Kim and Benjamin Snyder

55

LP 6b NLP Applications II → Hall 6 13.45 From Natural Language Specifications to Program Input Parsers Tao Lei, Fan Long, Regina Barzilay and Martin Rinard

14.10 Entity Linking for Tweets Xiaohua Liu, Yitong Li, Haocheng Wu, Ming Zhou, Furu Wei And Yi Lu

14.35 Identification of Speakers in Novels Hua He, Denilson Barbosa and Grzegorz Kondrak LP 6c Cognitive Modelling and Psycholinguistics / Lexical Semantics and Ontologies → Hall 7

13.45 Language Acquisition and Probabilistic Models: Keeping it Simple Aline Villavicencio, Marco Idiart, Robert Berwick and Igor Malioutov

14.10 A Two Level Model for Context Sensitive Inference Rules Oren Melamud, Jonathan Berant, Ido Dagan, Jacob Goldberger and Idan Szpektor

14.35 Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity Mohammad Taher Pilehvar, David Jurgens and Roberto Navigli

LP 6d Language Resources II / Machine Translation: Methods → Hall 8 13.45 Linking and Extending an Open Multilingual Wordnet Francis Bond and Ryan Foster

14.10 FrameNet on the Way to Babel: Creating a Bilingual FrameNet Using Wiktionary as Interlingual Connection Silvana Hartmann and Iryna Gurevych

14.35 Dirt Cheap Web-Scale Parallel Text from the Common Crawl Jason Smith, Herve Saint-Amand, Magdalena Plamada, Philipp Koehn, Chris Callison-Burch and Adam Lopez

LP 6e Summarization and Generation II → Hall 10

13.45 A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization Lu Wang, Hema Raghavan, Vittorio Castelli, Radu Florian and Claire Cardie

14.10 Domain-Independent Abstract Generation for Focused Meeting Summarization Lu Wang and Claire Cardie

14.35 A Statistical NLG Framework for Aggregated Planning and Realization Ravi Kondadadi, Blake Howald and Frank Schilder


54

LP 7a Machine Translation: Methods, Applications and Evaluations I → Hall 3 15.00 Models of Translation Competitions Mark Hopkins and Jon May

15.25 Learning a Phrase-based Translation Model from Monolingual Data with Application to Domain Adaptation Jiajun Zhang and Chengqing Zong

15.50 SenseSpotting: Never Let Your Parallel Data Tie you to an Old Domain Marine Carpuat, Hal Daume III, Katie Henry, Ann Irvine, Jagadeesh Jagarlamudi and Rachel Rudinger

LP 7b NLP Applications III → Hall 6 15.00 BRAINSUP: Brainstorming Support for Creative Sentence Generation Gozde Ozbal, Daniele Pighin and Carlo Strapparava

15.25 Grammatical Error Correction Using Integer Linear Programming Yuanbin Wu and Hwee Tou Ng

15.50 Text-Driven Toponym Resolution using Indirect Supervision Michael Speriosu and Jason Baldridge

LP 7c Text Mining and Information Extraction → Hall 7 15.00 Argument Inference from Relevant Event Mentions in Chinese Argument Extraction Peifeng Li, Qiaoming Zhu and Guodong Zhou

15.25 Fine-grained Semantic Typing of Emerging Entities Ndapandula Nakashole, Tomasz Tylenda and Gerhard Weikum

15.50 Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction Barbara Plank and Alessandro Moschitti

LP 7d Cognitive Modelling and Psycholinguistics / Phonology and Morphology → Hall 8 15.00 A Joint Model of Word Segmentation and Phonological Variation for English Word-final /t/-deletion Benjamin Börschinger, Mark Johnson and Katherine Demuth

15.25 Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics Angeliki Lazaridou, Marco Marelli, Roberto Zamparelli and Marco Baroni

15.50 Unsupervised Consonant-Vowel Prediction over Hundreds of Languages Young-Bum Kim and Benjamin Snyder

55

LP 7e Summarization and Generation III → Hall 10 15.00 Improving Text Simplification Language Modeling Using Unsimplified Text Data David Kauchak

15.25 Combining Referring Expression Generation and Surface Realization: A Corpus-Based Investigation of Architectures Sina Zarrieß and Jonas Kuhn

15.50 Named Entity Recognition using Cross-lingual Resources: Arabic as an Example Kareem Darwish 16.15 Coffee Break

SHORT PAPERS

SP 8a Machine Translation: Methods, Applications and Evaluations → Hall 3 16.45 Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation Kevin Duh, Graham Neubig, Katsuhito Sudoh and Hajime Tsukada

17.05 Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration Phillippe Langlais

17.25 Scalable Modified Kneser-Ney Language Model Estimation Kenneth Heafield, Ivan Pouzyrevsky, Jonathan Clark, Mohammed Mediani and Philipp Koehn

17.45 Incremental Topic-Based Translation Model Adaptation for Conversational Spoken Language Translation Sanjika Hewavitharana, Dennis Mehay, Sankaranarayanan Ananthakrishnan and Prem Natarajan


16.45 A Lightweight and High Performance Monolingual Word Aligner Xuchen Yao, Benjamin Van Durme, Chris Callison-Burch and Peter Clark

17.05 A Learner Corpus-based Approach to Verb Suggestion for ESL Yu Sawai, Mamoru Komachi and Yuji Matsumoto

17.25 Learning Semantic Textual Similarity with Structural Representations Aliaksei Severyn, Alessandro Moschitti and Massimo Nicosia

17.45 Typesetting for Improved Readability using Lexical and Syntactic Information Ahmed Salama, Kemal Oflazer and Susan Hagan


56

SP 8c Lexical Semantics and Ontologies → Hall 7

16.45 Annotation of Regular Polysemy and Underspecification Héctor Martínez Alonso, Bolette Sandford Pedersen and Núria Bel

17.05 Derivational Smoothing for Syntactic Distributional Semantics Sebastian Pado, Jan Snajder and Britta Zeller

17.25 Diathesis Alternation Approximation for Verb Clustering Lin Sun, Anna Korhonen and Diana McCarthy

17.45 Outsourcing FrameNet to the Crowd Marco Fossati, Claudio Giuliano and Sara Tonelli

SP 8d Evaluation Methods, Information Retrieval & Language Resources → Hall 8

16.45 Smatch: an Evaluation Metric for Semantic Feature Structures Shu Cai and Kevin Knight

17.05 Variable Bit Quantisation for LSH Sean Moran, Victor Lavrenko and Miles Osborne

17.25 Context Vector Disambiguation for Bilingual Lexicon Extraction from Comparable Corpora Dhouha Bouamor, Nasredine Semmar and Pierre Zweigenbaum

17.45 The Effects of Lexical Resource Quality on Preference Violation Detection Jesse Dunietz, Lori Levin and Jaime Carbonell

Student Research Workshop

SRW 8e Student Research Workshop → Hall 10 16.45 Robust Multilingual Statistical Morphological Generation Models Ondřej Dušek and Filip Jurčíček

17.05 A Corpus-based Evaluation Method for Distributional Semantic Models Abdellah Fourtassi and Emmanuel Dupoux

17.25 Deepfix: Statistical Post-editing of Statistical Machine Translation Using Deep Syntactic Analysis Rudolf Rosa, David Mareček and Aleš Tamchyna

18.30 Banquet (The Sheraton Hotel, Royal Hall & Sredets Hall)

57

LP 7e Summarization and Generation III → Hall 10 15.00 Improving Text Simplification Language Modeling Using Unsimplified Text Data David Kauchak

15.25 Combining Referring Expression Generation and Surface Realization: A Corpus-Based Investigation of Architectures Sina Zarrieß and Jonas Kuhn

15.50 Named Entity Recognition using Cross-lingual Resources: Arabic as an Example Kareem Darwish 16.15 Coffee Break

SHORT PAPERS

SP 8a Machine Translation: Methods, Applications and Evaluations → Hall 3 16.45 Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation Kevin Duh, Graham Neubig, Katsuhito Sudoh and Hajime Tsukada

17.05 Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration Phillippe Langlais

17.25 Scalable Modified Kneser-Ney Language Model Estimation Kenneth Heafield, Ivan Pouzyrevsky, Jonathan Clark, Mohammed Mediani and Philipp Koehn

17.45 Incremental Topic-Based Translation Model Adaptation for Conversational Spoken Language Translation Sanjika Hewavitharana, Dennis Mehay, Sankaranarayanan Ananthakrishnan and Prem Natarajan


16.45 A Lightweight and High Performance Monolingual Word Aligner Xuchen Yao, Benjamin Van Durme, Chris Callison-Burch and Peter Clark

17.05 A Learner Corpus-based Approach to Verb Suggestion for ESL Yu Sawai, Mamoru Komachi and Yuji Matsumoto

17.25 Learning Semantic Textual Similarity with Structural Representations Aliaksei Severyn, Alessandro Moschitti and Massimo Nicosia

17.45 Typesetting for Improved Readability using Lexical and Syntactic Information Ahmed Salama, Kemal Oflazer and Susan Hagan


56

SP 8c Lexical Semantics and Ontologies → Hall 7

16.45 Annotation of Regular Polysemy and Underspecification Héctor Martínez Alonso, Bolette Sandford Pedersen and Núria Bel

17.05 Derivational Smoothing for Syntactic Distributional Semantics Sebastian Pado, Jan Snajder and Britta Zeller

17.25 Diathesis Alternation Approximation for Verb Clustering Lin Sun, Anna Korhonen and Diana McCarthy

17.45 Outsourcing FrameNet to the Crowd Marco Fossati, Claudio Giuliano and Sara Tonelli

SP 8d Evaluation Methods, Information Retrieval & Language Resources → Hall 8

16.45 Smatch: an Evaluation Metric for Semantic Feature Structures Shu Cai and Kevin Knight

17.05 Variable Bit Quantisation for LSH Sean Moran, Victor Lavrenko and Miles Osborne

17.25 Context Vector Disambiguation for Bilingual Lexicon Extraction from Comparable Corpora Dhouha Bouamor, Nasredine Semmar and Pierre Zweigenbaum

17.45 The Effects of Lexical Resource Quality on Preference Violation Detection Jesse Dunietz, Lori Levin and Jaime Carbonell

Student Research Workshop

SRW 8e Student Research Workshop → Hall 10 16.45 Robust Multilingual Statistical Morphological Generation Models Ondřej Dušek and Filip Jurčíček

17.05 A Corpus-based Evaluation Method for Distributional Semantic Models Abdellah Fourtassi and Emmanuel Dupoux

17.25 Deepfix: Statistical Post-editing of Statistical Machine Translation Using Deep Syntactic Analysis Rudolf Rosa, David Mareček and Aleš Tamchyna

18.30 Banquet (The Sheraton Hotel, Royal Hall & Sredets Hall)

57

th Main Conference: Wed, August 7


9.30 – 10.30 Invited Lecture 3: Chantel Prat Hall 3




13.30 – 15.00 ACL Business Meeting Hall 3




18.30 – 19.15 Lifetime Achievement Award Session Hall 3

19.15 – 19.30 Closing Session Hall 319.30 End

Invited Talk: Chantel Prat (University of Washington)Individual Differences in Language and Executive Processes: How the Brain Keeps Track of Variables

thWednesday, August 7 , 2013, 9.30 am – 10.30 am Hall 3→Short Bio: Dr. Prat is an Assistant Professor in the Department of Psychology at University of Washington. She earned her Ph.D. at the University of California, Davis, working with Debra Long on investigations of individual differences in representation of discourse in the two hemispheres, and trained subsequently at the Center for Cognitive Brain Imaging with Marcel Just, conducting investigations of network-level characterizations of cognitive capacity. Dr. Prat's research investigates the nature of biological constraints on information processing, with an emphasis on the neural correlates of individual differences in language comprehension abilities. Her current research at the Cognition and Cortical Dynamics Laboratory employs the combination of fMRI, TMS, DTI, and behavioral paradigms to investigate the neural basis of individual differences in language and cognition.

Dr. Prat was named Young Investigator for 2011 by the Society for Text and Discourse. The purpose of this award is to recognize outstanding early career contributions to text and discourse research. Recipients have demonstrated exceptional and innovative contributions to discourse research and show superior promise as leaders in the field.




9.30 Invited Talk 3: Hall 3

Chantel Prat

10.30 Coffee Break


Machine NLP for the Web Sentiment Dialog & TACL I

Translation: & Social Web Analysis, Interactive

Methods, Opinion Mining Systems

Applications & & Text

Evaluations II Classification I

12.15 Lunch Break

13.30 ACL Business Hall 3

Meeting


Evaluation Question Sentiment Multilinguality � TACL II

Methods Answering Analysis, +

Extraction Multimodal NLP

Opinion Mining

& Text

Classification II

16.15 Coffee Break

16:45 Papers SP 11a SP 11b SP 11c LP 11d LP 11e

Text Mining & NPL Applications Sentiment Cognitive TACL III

Infornation NLP for the Web Analysis, Modeling &

Extraction & Social Media Extraction Psycholinguistics

Opinion Mining

& Text

Classification SP

18.30 Lifetime Hall 3 Achievement Award Session 19.15 Closing Session Hall 3

19.30 End

thProgram – Wed, August 7

58 59

th Main Conference: Wed, August 7


9.30 – 10.30 Invited Lecture 3: Chantel Prat Hall 3




13.30 – 15.00 ACL Business Meeting Hall 3




18.30 – 19.15 Lifetime Achievement Award Session Hall 3

19.15 – 19.30 Closing Session Hall 319.30 End

Invited Talk: Chantel Prat (University of Washington)Individual Differences in Language and Executive Processes: How the Brain Keeps Track of Variables

thWednesday, August 7 , 2013, 9.30 am – 10.30 am Hall 3→Short Bio: Dr. Prat is an Assistant Professor in the Department of Psychology at University of Washington. She earned her Ph.D. at the University of California, Davis, working with Debra Long on investigations of individual differences in representation of discourse in the two hemispheres, and trained subsequently at the Center for Cognitive Brain Imaging with Marcel Just, conducting investigations of network-level characterizations of cognitive capacity. Dr. Prat's research investigates the nature of biological constraints on information processing, with an emphasis on the neural correlates of individual differences in language comprehension abilities. Her current research at the Cognition and Cortical Dynamics Laboratory employs the combination of fMRI, TMS, DTI, and behavioral paradigms to investigate the neural basis of individual differences in language and cognition.

Dr. Prat was named Young Investigator for 2011 by the Society for Text and Discourse. The purpose of this award is to recognize outstanding early career contributions to text and discourse research. Recipients have demonstrated exceptional and innovative contributions to discourse research and show superior promise as leaders in the field.




9.30 Invited Talk 3: Hall 3

Chantel Prat

10.30 Coffee Break


Machine NLP for the Web Sentiment Dialog & TACL I

Translation: & Social Web Analysis, Interactive

Methods, Opinion Mining Systems

Applications & & Text

Evaluations II Classification I

12.15 Lunch Break

13.30 ACL Business Hall 3

Meeting


Evaluation Question Sentiment Multilinguality � TACL II

Methods Answering Analysis, +

Extraction Multimodal NLP

Opinion Mining

& Text

Classification II

16.15 Coffee Break

16:45 Papers SP 11a SP 11b SP 11c LP 11d LP 11e

Text Mining & NPL Applications Sentiment Cognitive TACL III

Infornation NLP for the Web Analysis, Modeling &

Extraction & Social Media Extraction Psycholinguistics

Opinion Mining

& Text

Classification SP

18.30 Lifetime Hall 3 Achievement Award Session 19.15 Closing Session Hall 3

19.30 End

thProgram – Wed, August 7

58 59

thExtended Daily Program – Wed, August 7



9.30 Invited Talk: Chantel Prat Individual Differences in Language and Executive Processes: How the Brain Keeps Track of Variables Hall 3→


LONG PAPERS, SHORT PAPERS, TACL


LONG PAPERS

LP 9a Machine Translation: Methods, Applications and Evaluations II → Hall 3

11.00 Beam Search for Solving Substitution Ciphers Malte Nuhn, Julian Schamper and Hermann Ney

11.25 Social Text Normalization using Contextual Graph Random Walks Hany Hassan and Arul Menezes

11.50 Integrating Phrase-based Reordering Features into Chart-based Decoder for Machine Translation Tthuylinh Nguyen and Stephan Vogel

LP 9b NLP for the Web and Social Web → Hall 6

11.00 Machine Translation Detection from Monolingual Web-Text Yuki Arase and Ming Zhou

11.25 Paraphrase-Driven Learning for Open Question Answering Anthony Fader, Luke Zettlemoyer and Oren Etzioni

11.50 Aid is Out There: Looking for Help from Tweets during a Large Scale Disaster Istvan Varga, Motoki Sano, Kentaro Torisawa, Chikara Hashimoto, Kiyonori Ohtake, Takao Kawai, Jong-Hoon Oh and Stijn De Saeger

LP 9c Sentiment Analysis, Opinion Mining and Text Classification I → Hall 7

11.00 A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations Angeliki Lazaridou, Ivan Titov and Caroline Sporleder

11.25 Joint Inference for Fine-grained Opinion Extraction Bishan Yang and Claire Cardie

11.50 Linguistic Models for Analyzing and Detecting Biased Language Marta Recasens, Cristian Danescu-Niculescu-Mizil and Dan Jurafsky

LP 9d Dialogue and Interactive Systems → Hall 8

11.00 Evaluating a City Exploration Dialogue System with Integrated Question-Answering and Pedestrian Navigation Srinivasan Janarthanam, Tiphaine Dalmas, Phil Bartie, Xingkun Liu, Oliver Lemon, Bonnie Webber and William Mackaness

11.25 Lightly Supervised Learning of Procedural Dialog Systems Svitlana Volkova, Pallavi Choudhury, Chris Quirk, Bill Dolan and Luke Zettlemoyer

11.50 Public Dialogue: Analysis of Tolerance in Online Discussions Arjun Mukherjee, Vivek Venkataraman, Bing Liu and Sharon Meraz

LP TACL I 9e → Hall 10

11.00 Weakly Supervised Part-of-Speech Tagging with Coupled Token and Type Constraints Oscar Täckström, Dipanjan Das, Slav Petrov, Ryan McDonald, Joakim Nivre

11.25 What Makes Writing Great? First Experiments on Article Quality Prediction in the Science Journalism Domain Annie Louis and Ani Nenkova

11.50 Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing Weiwei Sun, Xiaojun Wan 12.15 Lunch Break 13.30 ACL Business Meeting

LP 10a Evaluation Methods → Hall 3

15.00 Offspring from Reproduction Problems: What Replication Failure Teaches Us Antske Fokkens, Marieke van Erp, Marten Postma, Ted Pedersen, Piek Vossen and Nuno Freire

15.25 Evaluating Text Segmentation using Boundary Edit Distance Chris Fournier

15.50 Crowd Prefers the Middle Path: A New IAA Metric for Crowdsourcing Reveals Turker Biases in Query Segmentation Rohan Ramanath, Monojit Choudhury, Kalika Bali and Rishiraj Saha Roy

60 61

thExtended Daily Program – Wed, August 7



9.30 Invited Talk: Chantel Prat Individual Differences in Language and Executive Processes: How the Brain Keeps Track of Variables Hall 3→


LONG PAPERS, SHORT PAPERS, TACL


LONG PAPERS

LP 9a Machine Translation: Methods, Applications and Evaluations II → Hall 3

11.00 Beam Search for Solving Substitution Ciphers Malte Nuhn, Julian Schamper and Hermann Ney

11.25 Social Text Normalization using Contextual Graph Random Walks Hany Hassan and Arul Menezes

11.50 Integrating Phrase-based Reordering Features into Chart-based Decoder for Machine Translation Tthuylinh Nguyen and Stephan Vogel

LP 9b NLP for the Web and Social Web → Hall 6

11.00 Machine Translation Detection from Monolingual Web-Text Yuki Arase and Ming Zhou

11.25 Paraphrase-Driven Learning for Open Question Answering Anthony Fader, Luke Zettlemoyer and Oren Etzioni

11.50 Aid is Out There: Looking for Help from Tweets during a Large Scale Disaster Istvan Varga, Motoki Sano, Kentaro Torisawa, Chikara Hashimoto, Kiyonori Ohtake, Takao Kawai, Jong-Hoon Oh and Stijn De Saeger

LP 9c Sentiment Analysis, Opinion Mining and Text Classification I → Hall 7

11.00 A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations Angeliki Lazaridou, Ivan Titov and Caroline Sporleder

11.25 Joint Inference for Fine-grained Opinion Extraction Bishan Yang and Claire Cardie

11.50 Linguistic Models for Analyzing and Detecting Biased Language Marta Recasens, Cristian Danescu-Niculescu-Mizil and Dan Jurafsky

LP 9d Dialogue and Interactive Systems → Hall 8

11.00 Evaluating a City Exploration Dialogue System with Integrated Question-Answering and Pedestrian Navigation Srinivasan Janarthanam, Tiphaine Dalmas, Phil Bartie, Xingkun Liu, Oliver Lemon, Bonnie Webber and William Mackaness

11.25 Lightly Supervised Learning of Procedural Dialog Systems Svitlana Volkova, Pallavi Choudhury, Chris Quirk, Bill Dolan and Luke Zettlemoyer

11.50 Public Dialogue: Analysis of Tolerance in Online Discussions Arjun Mukherjee, Vivek Venkataraman, Bing Liu and Sharon Meraz

LP TACL I 9e → Hall 10

11.00 Weakly Supervised Part-of-Speech Tagging with Coupled Token and Type Constraints Oscar Täckström, Dipanjan Das, Slav Petrov, Ryan McDonald, Joakim Nivre

11.25 What Makes Writing Great? First Experiments on Article Quality Prediction in the Science Journalism Domain Annie Louis and Ani Nenkova

11.50 Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing Weiwei Sun, Xiaojun Wan 12.15 Lunch Break 13.30 ACL Business Meeting

LP 10a Evaluation Methods → Hall 3

15.00 Offspring from Reproduction Problems: What Replication Failure Teaches Us Antske Fokkens, Marieke van Erp, Marten Postma, Ted Pedersen, Piek Vossen and Nuno Freire

15.25 Evaluating Text Segmentation using Boundary Edit Distance Chris Fournier

15.50 Crowd Prefers the Middle Path: A New IAA Metric for Crowdsourcing Reveals Turker Biases in Query Segmentation Rohan Ramanath, Monojit Choudhury, Kalika Bali and Rishiraj Saha Roy

60 61

LP 10b Question Answering → Hall 6

15.00 Deceptive Answer Prediction with User Preference Graph Fangtao Li, Yang Gao, George Zhou, Xiance Si and Decheng Dai

15.25 Why-Question Answering using Intra- and Inter-Sentential Causal Relations Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Motoki Sano, Stijn De Saeger and Kiyonori Ohtake

15.50 Question Answering Using Enhanced Lexical Semantic Models Wen-tau Yih, Ming-Wei Chang, Christopher Meek and Andrzej Pastusiak

LP 10c Sentiment Analysis, Opinion Mining and Text Classification II → Hall 7 15.00 Syntactic Patterns versus Word Alignment: Extracting Opinion Targets from Online Reviews Kang Liu, Liheng Xu and Jun Zhao

15.25 Mining Opinion Words and Opinion Targets in a Two-Stage Framework Liheng Xu, Kang Liu, Siwei Lai, Yubo Chen and Jun Zhao

15.50 Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning Song Feng, Jun Seok Kang, Polina Kuznetsova and Yejin Choi

SP 10d Multilinguality + Multimodal NLP → Hall 8

15.00 Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks Jose Guilherme Camargo de Souza, Miquel Esplà-Gomis, Marco Turchi and Matteo Negri

15.35 An Information Theoretic Approach to Bilingual Word Clustering Manaal Faruqui and Chris Dyer

15.55 Building and Evaluating a Distributional Memory for Croatian Jan Snajder, Sebastian Pado and Zeljko Agic

16.15 Generalizing Image Captions for Image-Text Parallel Corpus Polina Kuznetsova, Vicente Ordonez, Alexander Berg, Tamara Berg and Yejin Choi

LP TACL II 10e → Hall 10

15.00 Grounding Action Descriptions in Videos Michaela Regneri, Marcus Rohrbach, Stefan Thater, Dominikus Wetzel, Bernt Schiele, Manfred Pinkal

15.25 Weakly-Supervised Max-Margin Grounded Language Acquisition Jayant Krishnamurthy, Thomas Kollar


62

15.50 Combining Distributional and Logical Semantics Mike Lewis, Mark Steedman 16.15 Coffee Break

SP 11a Text Mining and Information Extraction → Hall 3 16.45 Recognizing Identical Events with Graph Kernels Goran Glavaš and Jan Snajder

17.05 Automatic Term Ambiguity Detection Tyler Baldwin, Yunyao Li and Bogdan Alexe

17.25 Towards Accurate Distant Supervision for Relational Facts Extraction Xingxing Zhang, Jianwen Zhang, Junyu Zeng, Jun Yan, Zheng Chen and Zhifang Sui

17.45 Sequence Labeling for Determining Opinions in Online Forums Kazi Hasan and Vincent Ng

SP 11b NLP Applications / NLP for the Web and Social Media → Hall 6

16.45 Are School-of-thought Words Characterizable? Xiaorui Jiang, Xiaoping Sun, Hai Zhuge and Jianmin Yao

17.05 Identifying Opinion Subgroups in Arabic Online Discussions Amjad Abu-Jbara, Ben King, Mona Diab and Dragomir Radev

17.25 Extracting Events with Informal Temporal References in Personal Histories in Online Communities Miaomiao Wen, Zeyu Zheng, Hyeju Jang, Guang Xiang and Carolyn Rose

17.45 Multimodal DBN for Predicting High-Quality Answers in cQA portals Haifeng Hu, Bingquan Liu, Baoxun Wang, Ming Liu and Xiaolong Wang

SP 11c Sentiment Analysis, Opinion Mining and Text Classification SP → Hall 7

16.45 Bi-directional Inter-dependencies of Subjective Expressions and Targets and their Value for a Joint Model Roman Klinger and Philipp Cimiano

17.05 Identifying Sentiment Words Using an Optimization-based Model without Seed Words Hongliang Yu, Zhi-Hong Deng and Shiyingxue Li

17.25 Detecting Turnarounds in Sentiment Analysis: Thwarting Ankit Ramteke, Akshat Malu, Pushpak Bhattacharyya and Saketha Nath

17.45 Explicit and Implicit Syntactic Features for Text Classification Matt Post and Shane Bergsma

63

LP 10b Question Answering → Hall 6

15.00 Deceptive Answer Prediction with User Preference Graph Fangtao Li, Yang Gao, George Zhou, Xiance Si and Decheng Dai

15.25 Why-Question Answering using Intra- and Inter-Sentential Causal Relations Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Motoki Sano, Stijn De Saeger and Kiyonori Ohtake

15.50 Question Answering Using Enhanced Lexical Semantic Models Wen-tau Yih, Ming-Wei Chang, Christopher Meek and Andrzej Pastusiak

LP 10c Sentiment Analysis, Opinion Mining and Text Classification II → Hall 7 15.00 Syntactic Patterns versus Word Alignment: Extracting Opinion Targets from Online Reviews Kang Liu, Liheng Xu and Jun Zhao

15.25 Mining Opinion Words and Opinion Targets in a Two-Stage Framework Liheng Xu, Kang Liu, Siwei Lai, Yubo Chen and Jun Zhao

15.50 Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning Song Feng, Jun Seok Kang, Polina Kuznetsova and Yejin Choi

SP 10d Multilinguality + Multimodal NLP → Hall 8

15.00 Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks Jose Guilherme Camargo de Souza, Miquel Esplà-Gomis, Marco Turchi and Matteo Negri

15.35 An Information Theoretic Approach to Bilingual Word Clustering Manaal Faruqui and Chris Dyer

15.55 Building and Evaluating a Distributional Memory for Croatian Jan Snajder, Sebastian Pado and Zeljko Agic

16.15 Generalizing Image Captions for Image-Text Parallel Corpus Polina Kuznetsova, Vicente Ordonez, Alexander Berg, Tamara Berg and Yejin Choi

LP TACL II 10e → Hall 10

15.00 Grounding Action Descriptions in Videos Michaela Regneri, Marcus Rohrbach, Stefan Thater, Dominikus Wetzel, Bernt Schiele, Manfred Pinkal

15.25 Weakly-Supervised Max-Margin Grounded Language Acquisition Jayant Krishnamurthy, Thomas Kollar


62

15.50 Combining Distributional and Logical Semantics Mike Lewis, Mark Steedman 16.15 Coffee Break

SP 11a Text Mining and Information Extraction → Hall 3 16.45 Recognizing Identical Events with Graph Kernels Goran Glavaš and Jan Snajder

17.05 Automatic Term Ambiguity Detection Tyler Baldwin, Yunyao Li and Bogdan Alexe

17.25 Towards Accurate Distant Supervision for Relational Facts Extraction Xingxing Zhang, Jianwen Zhang, Junyu Zeng, Jun Yan, Zheng Chen and Zhifang Sui

17.45 Sequence Labeling for Determining Opinions in Online Forums Kazi Hasan and Vincent Ng

SP 11b NLP Applications / NLP for the Web and Social Media → Hall 6

16.45 Are School-of-thought Words Characterizable? Xiaorui Jiang, Xiaoping Sun, Hai Zhuge and Jianmin Yao

17.05 Identifying Opinion Subgroups in Arabic Online Discussions Amjad Abu-Jbara, Ben King, Mona Diab and Dragomir Radev

17.25 Extracting Events with Informal Temporal References in Personal Histories in Online Communities Miaomiao Wen, Zeyu Zheng, Hyeju Jang, Guang Xiang and Carolyn Rose

17.45 Multimodal DBN for Predicting High-Quality Answers in cQA portals Haifeng Hu, Bingquan Liu, Baoxun Wang, Ming Liu and Xiaolong Wang

SP 11c Sentiment Analysis, Opinion Mining and Text Classification SP → Hall 7

16.45 Bi-directional Inter-dependencies of Subjective Expressions and Targets and their Value for a Joint Model Roman Klinger and Philipp Cimiano

17.05 Identifying Sentiment Words Using an Optimization-based Model without Seed Words Hongliang Yu, Zhi-Hong Deng and Shiyingxue Li

17.25 Detecting Turnarounds in Sentiment Analysis: Thwarting Ankit Ramteke, Akshat Malu, Pushpak Bhattacharyya and Saketha Nath

17.45 Explicit and Implicit Syntactic Features for Text Classification Matt Post and Shane Bergsma

63

SP 11d Cognitive Modelling and Psycholinguistics → Hall 8

16.45 Does Korean Defeat Phonotactic Word Segmentation? Robert Daland and Kie Zuraw

17.05 Word Surprisal Predicts N400 Amplitude During Reading Stefan Frank, Leun Otten, Giulia Galli and Gabriella Vigliocco

17.25 Computerized Analysis of a Verbal Fluency Test James Ryan, Serguei Pakhomov, Susan Marino, Charles Bernick and Sarah Banks

17.45 A New Set of Norms for Semantic Relatedness Measures Sean Szumlanski, Fernando Gomez and Valerie Sims

LP TACL III 11e → Hall 10

16.45 Good, Great, Excellent: Global Ranking of Lexical Intensities with Web Semantics Gerard de Melo, Mohit Bansal

17.15 Using Pivot-based Paraphrasing and Intensity Enrichment to Improve a Subjectivity Lexicon for Essay Data Beata Beigman Klebanov, Jill Burstein, Nitin Madnani

17.35 Efficient Arc-factored Parsing of Syntactic and Semantic Dependencies Xavier Lluís, Xavier Carreras, Lluís Màrquez 18.30 Lifetime Achievement Award Session 19.15 Closing Session 19.30 End


64


CoNLL 2013SEVENTEENTH CONFERENCE ON

COMPUTATIONAL NATURAL LANGUAGE LEARNING

SP 11d Cognitive Modelling and Psycholinguistics → Hall 8

16.45 Does Korean Defeat Phonotactic Word Segmentation? Robert Daland and Kie Zuraw

17.05 Word Surprisal Predicts N400 Amplitude During Reading Stefan Frank, Leun Otten, Giulia Galli and Gabriella Vigliocco

17.25 Computerized Analysis of a Verbal Fluency Test James Ryan, Serguei Pakhomov, Susan Marino, Charles Bernick and Sarah Banks

17.45 A New Set of Norms for Semantic Relatedness Measures Sean Szumlanski, Fernando Gomez and Valerie Sims

LP TACL III 11e → Hall 10

16.45 Good, Great, Excellent: Global Ranking of Lexical Intensities with Web Semantics Gerard de Melo, Mohit Bansal

17.15 Using Pivot-based Paraphrasing and Intensity Enrichment to Improve a Subjectivity Lexicon for Essay Data Beata Beigman Klebanov, Jill Burstein, Nitin Madnani

17.35 Efficient Arc-factored Parsing of Syntactic and Semantic Dependencies Xavier Lluís, Xavier Carreras, Lluís Màrquez 18.30 Lifetime Achievement Award Session 19.15 Closing Session 19.30 End


64


CoNLL 2013SEVENTEENTH CONFERENCE ON

COMPUTATIONAL NATURAL LANGUAGE LEARNING

thThu, Aug 8 , 2013 → Hall 7 Overview

CoNLL 2013: August 8-9

8.00 – 10.30 Session 1


11.00 – 12.30 Session 2


14.00 – 15.30 Session 3

15.30 – 17.00 Poster session 1

17.00 – 18.00 Keynote 1 – Invited Talk: Ben Taskar

Program Committee

Conference Chairs Julia Hockenmaier Department of Computer Science University of Illinois at Urbana-Champaign

Sebastian Riedel Department of Computer Science University College London Shared Task Organizers Hwee Tou Ng (Chair), National University of Singapore Joel Tetreault, Nuance Communications Siew Mei Wu, National University of Singapore Yuanbin Wu, National University of Singapore Christian Hadiwinoto, National University of Singapore

SEVENTEENTH CONFERENCE ON COMPUTATIONAL NATURAL LANGUAGE LEARNING

66

Invited Talk: Ben Taskar (University of Washington)

Thursday, August 8 , 2013, 17.00 – 18.00 Hall 7th →Short Bio: Ben Taskar is an Associate Professor at the University of Washington. His primary research interests include machine learning, computational linguistics and computer vision. He received his B.A. and doctoral degree in Computer Science from Stanford University. After a postdoc at the University of California at Berkeley, he joined the faculty at the University of Pennsylvania's Computer and Information Science Department in 2007. He's been awarded the Sloan Research Fellowship, the NSF CAREER Award, and selected for the Young Investigator Program by the Office of Naval Research and the DARPA Computer Science Study Group.

67

thThu, Aug 8 , 2013 → Hall 7 Overview


8.00 – 10.30 Session 1


11.00 – 12.30 Session 2


14.00 – 15.30 Session 3

15.30 – 17.00 Poster session 1

17.00 – 18.00 Keynote 1 – Invited Talk: Ben Taskar

Program Committee

Conference Chairs Julia Hockenmaier Department of Computer Science University of Illinois at Urbana-Champaign

Sebastian Riedel Department of Computer Science University College London Shared Task Organizers Hwee Tou Ng (Chair), National University of Singapore Joel Tetreault, Nuance Communications Siew Mei Wu, National University of Singapore Yuanbin Wu, National University of Singapore Christian Hadiwinoto, National University of Singapore


66

Invited Talk: Ben Taskar (University of Washington)

Thursday, August 8 , 2013, 17.00 – 18.00 Hall 7th →Short Bio: Ben Taskar is an Associate Professor at the University of Washington. His primary research interests include machine learning, computational linguistics and computer vision. He received his B.A. and doctoral degree in Computer Science from Stanford University. After a postdoc at the University of California at Berkeley, he joined the faculty at the University of Pennsylvania's Computer and Information Science Department in 2007. He's been awarded the Sloan Research Fellowship, the NSF CAREER Award, and selected for the Young Investigator Program by the Office of Naval Research and the DARPA Computer Science Study Group.

67


68 69

8.30 – 10.30 Session 1

8.30 Opening Remarks

8.45 Online A�ive Learning for Cost Sensi�ve Domain Adapta�on Min Xiao and Yuhong Guo

9.00 Analysis of Stopping A�ive Learning based on Stabilizing Predi�ions Mi�ael Bloodgood and John Grothendie�

9.15 Improving Poin�ise Mu�al Informa�on (PMI) by Incorpora�ng Significant Co-occurrence Om Damani

9.30 Supervised Morphological Segmenta�on in a Low-Resource Learning Se�ng using Condi�onal Random Fields Teemu Ruokolainen, O�ar Kohonen, Sami Virpioja, Mikko Kurimo

9.45 Graph-Based Posterior Regulariza�on for Semi-Supervised S�u�ured Predi�ion Luheng He, Jennifer Gillenwater, Ben Ta�ar

10.00 A Boosted Semi-Markov Percep�on Tomoya Iwakura

10.15 Spe�ral Learning of Refinement HMMs Karl S�atos, Alexander Ru�, Shay B. Cohen, Mi�ael Collins


11.00 – 12.30 Session 2

11.00 Sentence Compression with Joint S�u�ural Inference Kapil Thadani and Kathleen McKeown Columbia Universi�

11.15 Learning Adaptable Pa�erns for Passage Reranking Aliaksei Severyn, Massimo Nicosia, Alessandro Mos�i�

11.30 Documents and Dependencies: an Explora�on of Ve�or Space Models for Seman�c Composi�on Alona Fy�e, Brian Murphy, Partha Talukdar, Tom Mit�ell

11.45 Hidden Markov Tree Models for Seman�c Class Indu�ion Edouard Grave, Guillaume Obozin�i, Francis Ba�

thExtended Daily Program – Thu, August 8 → Hall 712.00 Be�er Word Representa�ons with Recursive Neural Ne�orks for Morphology Thang Luong, Ri�ard So�er, Christopher Manning

12.15 Separa�ng Disambigua�on �om Composi�on in Distribu�onal Seman�cs Dimi�i Kartsaklis, Mehrnoo� Sadrzadeh, Stephen Pulman

12.30 – 14.00 Lun� Break

14.00 – 15.30 Session 3

14.00 Frame Seman�cs for Stance Classifica�on Kazi Saidul Hasan and Vincent Ng

14.15 Philosophers are Mortal: Inferring the Truth of Unseen Fa�s Gabor Angeli and Christopher Manning

14.30 Towards Robust Linguistic Analysis using OntoNotes Sameer Pradhan, Alessandro Mos�i�, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yu�en Zhang, Zhi Zhong

14.45 Dynamic Knowledge-Base Alignment for Coreference Resolu�on Jiaping Zheng, Luke Vilnis, Sameer Singh, Jinho D. Choi, Andrew McCallum

15.00 A Non-Monotonic Arc-Eager Transi�on System for Dependency Parsing Ma�hew Honnibal, Yoav Goldberg, Mark Johnson

15.15 Collapsed Varia�onal Bayesian Inference for PCFGs Pengyu Wang and Phil Blunsom

15.30 – 17.00 Poster Session 1

17.00 – 18.00 Keynote 1

17.00 Invited Talk: Ben Ta�ar


68 69

8.30 – 10.30 Session 1


8.45 Online A�ive Learning for Cost Sensi�ve Domain Adapta�on Min Xiao and Yuhong Guo

9.00 Analysis of Stopping A�ive Learning based on Stabilizing Predi�ions Mi�ael Bloodgood and John Grothendie�

9.15 Improving Poin�ise Mu�al Informa�on (PMI) by Incorpora�ng Significant Co-occurrence Om Damani

9.30 Supervised Morphological Segmenta�on in a Low-Resource Learning Se�ng using Condi�onal Random Fields Teemu Ruokolainen, O�ar Kohonen, Sami Virpioja, Mikko Kurimo

9.45 Graph-Based Posterior Regulariza�on for Semi-Supervised S�u�ured Predi�ion Luheng He, Jennifer Gillenwater, Ben Ta�ar

10.00 A Boosted Semi-Markov Percep�on Tomoya Iwakura

10.15 Spe�ral Learning of Refinement HMMs Karl S�atos, Alexander Ru�, Shay B. Cohen, Mi�ael Collins


11.00 – 12.30 Session 2

11.00 Sentence Compression with Joint S�u�ural Inference Kapil Thadani and Kathleen McKeown Columbia Universi�

11.15 Learning Adaptable Pa�erns for Passage Reranking Aliaksei Severyn, Massimo Nicosia, Alessandro Mos�i�

11.30 Documents and Dependencies: an Explora�on of Ve�or Space Models for Seman�c Composi�on Alona Fy�e, Brian Murphy, Partha Talukdar, Tom Mit�ell

11.45 Hidden Markov Tree Models for Seman�c Class Indu�ion Edouard Grave, Guillaume Obozin�i, Francis Ba�

thExtended Daily Program – Thu, August 8 → Hall 712.00 Be�er Word Representa�ons with Recursive Neural Ne�orks for Morphology Thang Luong, Ri�ard So�er, Christopher Manning

12.15 Separa�ng Disambigua�on �om Composi�on in Distribu�onal Seman�cs Dimi�i Kartsaklis, Mehrnoo� Sadrzadeh, Stephen Pulman

12.30 – 14.00 Lun� Break

14.00 – 15.30 Session 3

14.00 Frame Seman�cs for Stance Classifica�on Kazi Saidul Hasan and Vincent Ng

14.15 Philosophers are Mortal: Inferring the Truth of Unseen Fa�s Gabor Angeli and Christopher Manning

14.30 Towards Robust Linguistic Analysis using OntoNotes Sameer Pradhan, Alessandro Mos�i�, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yu�en Zhang, Zhi Zhong

14.45 Dynamic Knowledge-Base Alignment for Coreference Resolu�on Jiaping Zheng, Luke Vilnis, Sameer Singh, Jinho D. Choi, Andrew McCallum

15.00 A Non-Monotonic Arc-Eager Transi�on System for Dependency Parsing Ma�hew Honnibal, Yoav Goldberg, Mark Johnson

15.15 Collapsed Varia�onal Bayesian Inference for PCFGs Pengyu Wang and Phil Blunsom

15.30 – 17.00 Poster Session 1

17.00 – 18.00 Keynote 1

17.00 Invited Talk: Ben Ta�ar

thFri, Aug 9 , 2013 → Hall 7 Overview8.45 – 9.00 Session 4


11.00 – 12.30 Shared Task Orals


14.00 – 15.00 Keynote 2 – Invited Talk: Roger Levy

15.00 – 15.30 Best Paper Award

15.30 – 17.00 Poster Session 2 (incl. Shared Task) 17.00 Business Meeting


Invited Talk: Roger Levy (University of California, San Diego)

thFriday, August , 2013, Hall 79 14.00 – 15.00 →Short Bio: Roger Levy is an Associate Professor at the Department of Linguistics, University of California, San Diego, where he heads the Computational Psycholinguistics Lab. He got a B.Sc. Degree in Mathematics from the University of Arizona (1996) and an M.Sc. in Anthropological Sciences (2002) from Stanford University where he went on to defend a Ph.D. thesis in Linguistics (2005). His research focuses on theoretical and applied questions in the processing of natural language. He takes a special interest in the application of computational modeling and psycholinguistic experimentation to address the understanding of the cognitive underpinning of language processing and to facilitate the design of models and algorithms allowing machines to process human language. Professor Levy is recipient of the Alfred P. Sloan Research Fellowship (2012–2014) and the NSF Faculty Early Career Development (CAREER) Award (2010–2015).

70 71



8.45 – 10.30 Session 4

8.45 Polyglot: Distributed Word Representations for Multilingual NLP Rami Al-Rfou, Bryan Perozzi, Steven Skiena

9.00 Exploiting Multiple Hypotheses for Multilingual Spoken Language Understanding Marcos Calvo, Fernando García, Lluís-F. Hurtado, Santiago Jiménez, Emilio Sanchis

9.15 Multilingual WSD-like Constraints for Paraphrase Extraction Wilker Aziz and Lucia Specia

9.30 Topic Models + Word Alignment = A Flexible Framework for Extracting Bilingual Dictionary from Comparable Corpus Xiaodong Liu, Kevin Duh, Yuji Matsumoto

9.45 Terminology Extraction Approaches for Product Aspect Detection in Customer Reviews Jürgen Broß and Heiko Ehrig

10.00 – 10.30 Shared Task Overview

The CoNLL-2013 Shared Task on Grammatical Error Correction Hwee Tou Ng, Siew MeiWu, YuanbinWu, Christian Hadiwinoto and Joel Tetreault



11.00 The University of Illinois System in the CoNLL-2013 Shared Task Alla Rozovskaya, Kai-Wei Chang, Mark Sammons and Dan Roth

11.10 CoNLL-2013 Shared Task: Grammatical Error Correction NTHU System Description Ting-hui Kao, Yu-wei Chang, Hsun-wen Chiu, Tzu-Hsi Yen, Joanne Boisson, Jiancheng Wu and Jason S. Chang

11.20 NAIST at 2013 CoNLL Grammatical Error Correction Shared Task Ippei Yoshimoto, Tomoya Kose, Kensuke Mitsuzawa, Keisuke Sakaguchi, Tomoya Mizumoto, Yuta Hayashibe, Mamoru Komachi and Yuji Matsumoto

11.30 UM-Checker: A Hybrid System for English Grammatical Error Correction Junwen Xing, Longyue Wang, Derek F. Wong, Lidia S. Chao and Xiaodong Zeng

thExtended Daily Program – Fri, August 9 → Hall 7

thFri, Aug 9 , 2013 → Hall 7 Overview8.45 – 9.00 Session 4




14.00 – 15.00 Keynote 2 – Invited Talk: Roger Levy


15.30 – 17.00 Poster Session 2 (incl. Shared Task) 17.00 Business Meeting


Invited Talk: Roger Levy (University of California, San Diego)

thFriday, August , 2013, Hall 79 14.00 – 15.00 →Short Bio: Roger Levy is an Associate Professor at the Department of Linguistics, University of California, San Diego, where he heads the Computational Psycholinguistics Lab. He got a B.Sc. Degree in Mathematics from the University of Arizona (1996) and an M.Sc. in Anthropological Sciences (2002) from Stanford University where he went on to defend a Ph.D. thesis in Linguistics (2005). His research focuses on theoretical and applied questions in the processing of natural language. He takes a special interest in the application of computational modeling and psycholinguistic experimentation to address the understanding of the cognitive underpinning of language processing and to facilitate the design of models and algorithms allowing machines to process human language. Professor Levy is recipient of the Alfred P. Sloan Research Fellowship (2012–2014) and the NSF Faculty Early Career Development (CAREER) Award (2010–2015).

70 71



8.45 – 10.30 Session 4

8.45 Polyglot: Distributed Word Representations for Multilingual NLP Rami Al-Rfou, Bryan Perozzi, Steven Skiena

9.00 Exploiting Multiple Hypotheses for Multilingual Spoken Language Understanding Marcos Calvo, Fernando García, Lluís-F. Hurtado, Santiago Jiménez, Emilio Sanchis

9.15 Multilingual WSD-like Constraints for Paraphrase Extraction Wilker Aziz and Lucia Specia

9.30 Topic Models + Word Alignment = A Flexible Framework for Extracting Bilingual Dictionary from Comparable Corpus Xiaodong Liu, Kevin Duh, Yuji Matsumoto

9.45 Terminology Extraction Approaches for Product Aspect Detection in Customer Reviews Jürgen Broß and Heiko Ehrig

10.00 – 10.30 Shared Task Overview

The CoNLL-2013 Shared Task on Grammatical Error Correction Hwee Tou Ng, Siew MeiWu, YuanbinWu, Christian Hadiwinoto and Joel Tetreault



11.00 The University of Illinois System in the CoNLL-2013 Shared Task Alla Rozovskaya, Kai-Wei Chang, Mark Sammons and Dan Roth

11.10 CoNLL-2013 Shared Task: Grammatical Error Correction NTHU System Description Ting-hui Kao, Yu-wei Chang, Hsun-wen Chiu, Tzu-Hsi Yen, Joanne Boisson, Jiancheng Wu and Jason S. Chang

11.20 NAIST at 2013 CoNLL Grammatical Error Correction Shared Task Ippei Yoshimoto, Tomoya Kose, Kensuke Mitsuzawa, Keisuke Sakaguchi, Tomoya Mizumoto, Yuta Hayashibe, Mamoru Komachi and Yuji Matsumoto

11.30 UM-Checker: A Hybrid System for English Grammatical Error Correction Junwen Xing, Longyue Wang, Derek F. Wong, Lidia S. Chao and Xiaodong Zeng

thExtended Daily Program – Fri, August 9 → Hall 7

11.40 A Tree Transducer Model for Grammatical Error Correction Jan Buys and Brink van der Merwe

11.50 Constrained Grammatical Error Correction using Statistical Machine Translation Zheng Yuan and Mariano Felice

12.00 Shared Task Discussion


14.00 – 15.00 Keynote 2

14.00 Invited Talk: Roger Levy


15.00 Acquisition of Desires before Beliefs: A Computional Investigation Libby Barak, Afsaneh Fazly, Suzanne Stevenson

15.30 – 17.00 Poster Session 2 (incl. Shared Task)

LFG-based Features for Noun Number and Article Grammatical ErrorsGabor Berend, Veronika Vincze, Sina Zarrieß and Richárd Farkas

Toward More Precision in Correction of Grammatical ErrorsDan Flickinger and Jiye Yu

Grammatical Error Correction as Multiclass Classification with Single ModelZhongye Jia, Peilu Wang and Hai Zhao

IITB System for CoNLL 2013 Shared Task: A Hybrid Approach to Grammatical Error CorrectionAnoop Kunchukuttan, Ritesh Shah and Pushpak Bhattacharyya

UdS at CoNLL 2013 Shared TaskDesmond Darma Putra and Lili Szabo

Rule-based System for Automatic Grammar Correction Using Syntactic N-grams for English Language Learning (L2)Grigori Sidorov, Anubhav Gupta, Martin Tozer, Dolors Catala, Angels Catena and Sandrine Fuentes

Memory-based Grammatical Error CorrectionAntal van den Bosch and Peter Berck

A Noisy Channel Model Framework for Grammatical CorrectionL. Amber Wilcox-O’Hearn

A Hybrid Model For Grammatical Error CorrectionYang Xiang, Bo Yuan, Yaoyun Zhang, Xiaolong Wang, Wen Zheng and Chongqiang Wei

KUNLP Grammatical Error Correction System For CoNLL-2013 Shared TaskBong-Jun Yi, Ho-Chang Lee and Hae-Chang Rim

17.00 Business Meeting


72 73

11.40 A Tree Transducer Model for Grammatical Error Correction Jan Buys and Brink van der Merwe

11.50 Constrained Grammatical Error Correction using Statistical Machine Translation Zheng Yuan and Mariano Felice

12.00 Shared Task Discussion


14.00 – 15.00 Keynote 2

14.00 Invited Talk: Roger Levy


15.00 Acquisition of Desires before Beliefs: A Computional Investigation Libby Barak, Afsaneh Fazly, Suzanne Stevenson

15.30 – 17.00 Poster Session 2 (incl. Shared Task)

LFG-based Features for Noun Number and Article Grammatical ErrorsGabor Berend, Veronika Vincze, Sina Zarrieß and Richárd Farkas

Toward More Precision in Correction of Grammatical ErrorsDan Flickinger and Jiye Yu

Grammatical Error Correction as Multiclass Classification with Single ModelZhongye Jia, Peilu Wang and Hai Zhao

IITB System for CoNLL 2013 Shared Task: A Hybrid Approach to Grammatical Error CorrectionAnoop Kunchukuttan, Ritesh Shah and Pushpak Bhattacharyya

UdS at CoNLL 2013 Shared TaskDesmond Darma Putra and Lili Szabo

Rule-based System for Automatic Grammar Correction Using Syntactic N-grams for English Language Learning (L2)Grigori Sidorov, Anubhav Gupta, Martin Tozer, Dolors Catala, Angels Catena and Sandrine Fuentes

Memory-based Grammatical Error CorrectionAntal van den Bosch and Peter Berck

A Noisy Channel Model Framework for Grammatical CorrectionL. Amber Wilcox-O’Hearn

A Hybrid Model For Grammatical Error CorrectionYang Xiang, Bo Yuan, Yaoyun Zhang, Xiaolong Wang, Wen Zheng and Chongqiang Wei

KUNLP Grammatical Error Correction System For CoNLL-2013 Shared TaskBong-Jun Yi, Ho-Chang Lee and Hae-Chang Rim

17.00 Business Meeting


72 73

BioNLP 2013 th thThursday, Friday, August 8 -9 , 2013 → Hall 6

WORKSHOP PROGRAM:thThursday, August 8

8.40 – 8.50 Opening Remarks

Session 1: Clinical Text Processing

8.50 – 9.10 Earlier Identification of Epilepsy Surgery Candidates Using Natural Language Processing Pawel Matykiewicz, Kevin Cohen, Katherine D. Holland, Tracy A. Glauser, Shannon M. Standridge, Karen M. Verspoor and John Pestian

9.10 – 9.30 Identification of Patients with Acute Lung Injury from Free-Text Chest X-Ray Reports Meliha Yetisgen-Yildiz, Cosmin Bejan and Mark Wurfel

9.30 – 9.50 Discovering Temporal Narrative Containers in Clinical Text Timothy Miller, Steven Bethard, Dmitriy Dligach, Sameer Pradhan, Chen Lin and Guergana Savova

9.50 – 10.10 Identifying Pathological Findings in German Radiology Reports Using a Syntacto-semantic Parsing Approach Claudia Bretschneider, Sonja Zillner and Matthias Hammon

10.10 – 10.30 Corpus-Driven Terminology Development: Populating Swedish SNOMED CT with Synonyms Extracted from Electronic Health Records Aron Henriksson, Maria Skeppstedt, Maria Kvist, Martin Duneld and Mike Conway

10.30 – 11.00 Morning coffee break

11.00 – 12.00 Invited Talk by Galia Angelova

12.00 – 12.30 BioNLP Shared Task Overview by Claire Nedellec


Session 2: Biomedical Language Processing

14.00 – 14.20 Exploring Word Class N-grams to Measure Language Development in Children Gabriela Ramirez-de-la-Rosa, Thamar Solorio, Manuel Montes, Yang Liu, Lisa Bedore, Elizabeth Pena and Aquiles Iglesias

14.20 – 14.40 Interpreting Consumer Health Questions: The Role of Anaphora and Ellipsis Halil Kilicoglu, Marcelo Fiszman and Dina Demner-Fushman

Workshop 1:

75

th th Workshops: August 8 -9

Overviewth th2-day Workshops: August 8 -9 , 2013

W1: BioNLP 2013 Hall 6 W2: ENLG 2013: 14th European Workshop on Natural Language Generation Hall 1.7 W3: WMT 2013: 8th Workshop on Statistical Machine Translation Hall 8 W4: LAW VII & ID: 7th Linguistic Annotation Workshop & Interoperability with Discourse Hall 3.1W5: BSNLP 2013: The 4th Biennial Workshop on Balto-Slavic Natural Language Processing Hall 3.2

th1-day Workshops on August 8 , 2013

W6: BUCC 2013: 6th Workshop on Building and Using Comparable Corpora Hall 1.2 W7: CMCL 2013: Cognitive Modeling and Computational Linguistics Hall 10W8: LaTeCH 2013: Language Technology for Cultural Heritage, Social Sciences, and Humanities Hall 4W9: HYTRA 2013: Second Workshop on Hybrid Approaches to Translation Hall 1.4W10: PITR 2013: 2nd Workshop on Predicting and Improving Text Readability for Target Reader Populations Hall 1.5


W11: MoL 2013: The 13th Meeting on the Mathematics of Language Hall 1.2W12: MULTILING 2013: Multilingual Multi-Document Summarization Hall 1.4 W13: CVSC 2013: Workshop on Continuous Vector Space Models and their Compositionality Hall 10W14: DiscoMT 2013: Discourse in Machine Translation Hall 4W15: Teaching NLP: Teaching NLP and CL Hall 1.5

74


BioNLP 2013 th thThursday, Friday, August 8 -9 , 2013 → Hall 6



Session 1: Clinical Text Processing

8.50 – 9.10 Earlier Identification of Epilepsy Surgery Candidates Using Natural Language Processing Pawel Matykiewicz, Kevin Cohen, Katherine D. Holland, Tracy A. Glauser, Shannon M. Standridge, Karen M. Verspoor and John Pestian

9.10 – 9.30 Identification of Patients with Acute Lung Injury from Free-Text Chest X-Ray Reports Meliha Yetisgen-Yildiz, Cosmin Bejan and Mark Wurfel

9.30 – 9.50 Discovering Temporal Narrative Containers in Clinical Text Timothy Miller, Steven Bethard, Dmitriy Dligach, Sameer Pradhan, Chen Lin and Guergana Savova

9.50 – 10.10 Identifying Pathological Findings in German Radiology Reports Using a Syntacto-semantic Parsing Approach Claudia Bretschneider, Sonja Zillner and Matthias Hammon

10.10 – 10.30 Corpus-Driven Terminology Development: Populating Swedish SNOMED CT with Synonyms Extracted from Electronic Health Records Aron Henriksson, Maria Skeppstedt, Maria Kvist, Martin Duneld and Mike Conway

10.30 – 11.00 Morning coffee break

11.00 – 12.00 Invited Talk by Galia Angelova

12.00 – 12.30 BioNLP Shared Task Overview by Claire Nedellec


Session 2: Biomedical Language Processing

14.00 – 14.20 Exploring Word Class N-grams to Measure Language Development in Children Gabriela Ramirez-de-la-Rosa, Thamar Solorio, Manuel Montes, Yang Liu, Lisa Bedore, Elizabeth Pena and Aquiles Iglesias

14.20 – 14.40 Interpreting Consumer Health Questions: The Role of Anaphora and Ellipsis Halil Kilicoglu, Marcelo Fiszman and Dina Demner-Fushman

Workshop 1:

75

th th Workshops: August 8 -9

Overviewth th2-day Workshops: August 8 -9 , 2013

W1: BioNLP 2013 Hall 6 W2: ENLG 2013: 14th European Workshop on Natural Language Generation Hall 1.7 W3: WMT 2013: 8th Workshop on Statistical Machine Translation Hall 8 W4: LAW VII & ID: 7th Linguistic Annotation Workshop & Interoperability with Discourse Hall 3.1W5: BSNLP 2013: The 4th Biennial Workshop on Balto-Slavic Natural Language Processing Hall 3.2


W6: BUCC 2013: 6th Workshop on Building and Using Comparable Corpora Hall 1.2 W7: CMCL 2013: Cognitive Modeling and Computational Linguistics Hall 10W8: LaTeCH 2013: Language Technology for Cultural Heritage, Social Sciences, and Humanities Hall 4W9: HYTRA 2013: Second Workshop on Hybrid Approaches to Translation Hall 1.4W10: PITR 2013: 2nd Workshop on Predicting and Improving Text Readability for Target Reader Populations Hall 1.5


W11: MoL 2013: The 13th Meeting on the Mathematics of Language Hall 1.2W12: MULTILING 2013: Multilingual Multi-Document Summarization Hall 1.4 W13: CVSC 2013: Workshop on Continuous Vector Space Models and their Compositionality Hall 10W14: DiscoMT 2013: Discourse in Machine Translation Hall 4W15: Teaching NLP: Teaching NLP and CL Hall 1.5

74


9.10 – 9.30 TEES 2.1: Automated Annotation Scheme Learning in the BioNLP 2013 Shared Task Jari Björne and Tapio Salakoski

9.30 – 9.50 EVEX in ST'13: Application of a Large-scale Text Mining Resource to Event Extraction and Network Construction Kai Hakala, Sofie Van Landeghem, Tapio Salakoski, Yves Van de Peer and Filip Ginter

9.50 – 10.10 Extracting Biomedical Events and Modifications Using Subgraph Matching with Noisy Training Data Andrew MacKinlay, David Martinez, Antonio Jimeno Yepes, Haibin Liu, W John Wilbur and Karin Verspoor

10.10 – 10.30 Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities Xiao Liu, Antoine Bordes and Yves Grandvalet

10.30 – 11.00 Break

Session 2: Oral Presentations: Cancer Genetics and Pathway Curation

11.00 – 11.10 GRO Task: Populating the Gene Regulation Ontology with events and relations Jung-Jae Kim, Xu Han, Vivian Lee and Dietrich Rebholz-Schuhmann

11.10 – 11.20 Overview of the Cancer Genetics (CG) task of BioNLP Shared Task 2013 Sampo Pyysalo, Tomoko Ohta and Sophia Ananiadou

11.20 – 11.30 Overview of the Pathway Curation (PC) task of BioNLP Shared Task 2013 Tomoko Ohta, Sampo Pyysalo, Rafal Rak, Andrew Rowley, Hong-Woo Chun, Sung-Jae Jung, Sung-Pil Choi, Sophia Ananiadou and Jun'ichi Tsujii

11.30 – 11.50 Generalizing an Approximate Subgraph Matching-based System to Extract Events in Molecular Biology and Cancer Genetics Haibin Liu, Karin Verspoor, Donald C. Comeau, Andrew MacKinlay and W John Wilbur

11.50 – 12.10 Performance and Limitations of the Linguistically Motivated Cocoa/ Peaberry System in a Broad Biological Domain SV Ramanan and P. Senthil Nathan

12.10 – 12.30 NaCTeM EventMine for BioNLP 2013 CG and PC tasks Makoto Miwa and Sophia Ananiadou

12.30-14:00 Lunch Break

Session 3: Posters

BioNLP Shared Task 2013: Supporting ResourcesPontus Stenetorp, Wiktoria Golik, Thierry Hamon, Donald C. Comeau, Rezarta Islamaj Dogan, Haibin Liu and W John Wilbur

A fast rule-based approach for biomedical event extractionQuoc-Chinh Bui, David Campos, Erik van Mulligen and Jan Kors

Improving Feature-Based Biomedical Event Extraction System by Integrating Argument InformationLishuang Li, Yiwen Wang and Degen Huang

77

14.40 – 15.00 Evaluating Large-scale Text Mining Applications Beyond the Traditional Numeric Performance Measures Sofie Van Landeghem, Suwisa Kaewphan, Filip Ginter and Yves Van de Peer

15.00 – 15.20 Recognizing Sublanguages in Scientific Journal Articles through Closure Properties Irina Temnikova and Kevin Cohen

15.30 – 16.00 Afternoon coffee break

16.00 – 16.20 BEL Networks Derived from Qualitative Translations of BioNLP Shared Task Annotations Juliane Fluck, Alexander Klenner, Sumit Madan, Sam Ansari, Tamara Bobic, Julia Hoeng, Martin Hofmann-Apitius and Manuel Peitsch

16.20 – 16.40 Unsupervised Linguistically-Driven Reliable Dependency Parses Detection and Self-Training for Adaptation to the Biomedical Domain Felice Dell'Orletta, Giulia Venturi and Simonetta Montemagni

16.40 – 17.30 Poster Session Adapting a Parser to Clinical Text by Simple Pre-processing RulesMaria Skeppstedt

Using the Argumentative Structure of Scientific Literature to Improve Information AccessAntonio Jimeno Yepes, James Mork and Alan Aronson

Using Latent Dirichlet Allocation for Child Narrative AnalysisKhairun-nisa Hassanali, Yang Liu and Thamar Solorio

Effect of Out Of Vocabulary Terms on Inferring Eligibility Criteria for a Retrospective Study in Hebrew EHRRaphael Cohen and Michael Elhadad

Parallels between Linguistics and BiologySutanu Chakraborti and Ashish Tendulkar

thFriday, Aug ust 9 – BioNLP Shared Task 2013

8.30-9.00 Welcome and Introduction

8.45 Overview of BioNLP Shared Task 2013 Claire Nédellec, Robert Bossy, Jin-Dong Kim, Jung-Jae Kim, Tomoko Ohta, Sampo Pyysalo and Pierre Zweigenbaum

Session 1: Oral Presentations: Genia Event Extraction and Gene Regulation Ontology

9.00 – 9.10 The Genia Event Extraction Shared Task, 2013 Edition - Overview Jin-Dong Kim, Yue Wang and Yamamoto Yasunori

76

WORKSHOP 1

9.10 – 9.30 TEES 2.1: Automated Annotation Scheme Learning in the BioNLP 2013 Shared Task Jari Björne and Tapio Salakoski

9.30 – 9.50 EVEX in ST'13: Application of a Large-scale Text Mining Resource to Event Extraction and Network Construction Kai Hakala, Sofie Van Landeghem, Tapio Salakoski, Yves Van de Peer and Filip Ginter

9.50 – 10.10 Extracting Biomedical Events and Modifications Using Subgraph Matching with Noisy Training Data Andrew MacKinlay, David Martinez, Antonio Jimeno Yepes, Haibin Liu, W John Wilbur and Karin Verspoor

10.10 – 10.30 Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities Xiao Liu, Antoine Bordes and Yves Grandvalet

10.30 – 11.00 Break

Session 2: Oral Presentations: Cancer Genetics and Pathway Curation

11.00 – 11.10 GRO Task: Populating the Gene Regulation Ontology with events and relations Jung-Jae Kim, Xu Han, Vivian Lee and Dietrich Rebholz-Schuhmann

11.10 – 11.20 Overview of the Cancer Genetics (CG) task of BioNLP Shared Task 2013 Sampo Pyysalo, Tomoko Ohta and Sophia Ananiadou

11.20 – 11.30 Overview of the Pathway Curation (PC) task of BioNLP Shared Task 2013 Tomoko Ohta, Sampo Pyysalo, Rafal Rak, Andrew Rowley, Hong-Woo Chun, Sung-Jae Jung, Sung-Pil Choi, Sophia Ananiadou and Jun'ichi Tsujii

11.30 – 11.50 Generalizing an Approximate Subgraph Matching-based System to Extract Events in Molecular Biology and Cancer Genetics Haibin Liu, Karin Verspoor, Donald C. Comeau, Andrew MacKinlay and W John Wilbur

11.50 – 12.10 Performance and Limitations of the Linguistically Motivated Cocoa/ Peaberry System in a Broad Biological Domain SV Ramanan and P. Senthil Nathan

12.10 – 12.30 NaCTeM EventMine for BioNLP 2013 CG and PC tasks Makoto Miwa and Sophia Ananiadou

12.30-14:00 Lunch Break

Session 3: Posters

BioNLP Shared Task 2013: Supporting ResourcesPontus Stenetorp, Wiktoria Golik, Thierry Hamon, Donald C. Comeau, Rezarta Islamaj Dogan, Haibin Liu and W John Wilbur

A fast rule-based approach for biomedical event extractionQuoc-Chinh Bui, David Campos, Erik van Mulligen and Jan Kors

Improving Feature-Based Biomedical Event Extraction System by Integrating Argument InformationLishuang Li, Yiwen Wang and Degen Huang

77

14.40 – 15.00 Evaluating Large-scale Text Mining Applications Beyond the Traditional Numeric Performance Measures Sofie Van Landeghem, Suwisa Kaewphan, Filip Ginter and Yves Van de Peer

15.00 – 15.20 Recognizing Sublanguages in Scientific Journal Articles through Closure Properties Irina Temnikova and Kevin Cohen

15.30 – 16.00 Afternoon coffee break

16.00 – 16.20 BEL Networks Derived from Qualitative Translations of BioNLP Shared Task Annotations Juliane Fluck, Alexander Klenner, Sumit Madan, Sam Ansari, Tamara Bobic, Julia Hoeng, Martin Hofmann-Apitius and Manuel Peitsch

16.20 – 16.40 Unsupervised Linguistically-Driven Reliable Dependency Parses Detection and Self-Training for Adaptation to the Biomedical Domain Felice Dell'Orletta, Giulia Venturi and Simonetta Montemagni

16.40 – 17.30 Poster Session Adapting a Parser to Clinical Text by Simple Pre-processing RulesMaria Skeppstedt

Using the Argumentative Structure of Scientific Literature to Improve Information AccessAntonio Jimeno Yepes, James Mork and Alan Aronson

Using Latent Dirichlet Allocation for Child Narrative AnalysisKhairun-nisa Hassanali, Yang Liu and Thamar Solorio

Effect of Out Of Vocabulary Terms on Inferring Eligibility Criteria for a Retrospective Study in Hebrew EHRRaphael Cohen and Michael Elhadad

Parallels between Linguistics and BiologySutanu Chakraborti and Ashish Tendulkar

thFriday, August 9

8.30-9.00 Welcome and Introduction

8.45 Overview of BioNLP Shared Task 2013 Claire Nédellec, Robert Bossy, Jin-Dong Kim, Jung-Jae Kim, Tomoko Ohta, Sampo Pyysalo and Pierre Zweigenbaum

Session 1: Oral Presentations: Genia Event Extraction and Gene Regulation Ontology

9.00 – 9.10 The Genia Event Extraction Shared Task, 2013 Edition - Overview Jin-Dong Kim, Yue Wang and Yamamoto Yasunori

76

WORKSHOP 1

ENLG 2013: 14th European Workshop on Natural Language Generationth thThursday, Friday, August 8 -9 , 2013 → Hall 1.7



Session 1: NLG from Semantic Representations and Knowledge Bases

9.00 – 9.30 Aligning Formal Meaning Representations with Surface Strings for Wide-Coverage Text Generation Valerio Basile and Johan Bos

9.30 – 10.00 Exploiting Ontology Lexica for Generating Natural Language Texts from RDF Data Philipp Cimiano, Janna Lüker, David Nagel and Christina Unger

10.00 – 10.30 User-Controlled, Robust Natural Language Generation from an Evolving Knowledge Base Eva Banik, Eric Kow and Vinay Chaudhri


Session 2: Realisation, Aggregation and Variation

11.00 – 11.30 Enhancing the Expression of Contrast in the SPaRKy Restaurant Corpus David Howcroft, Crystal Nakatsu and Michael White

11.30 – 12.00 Generating Elliptic Coordination Claire Gardent and Shashi Narayan

12.00 – 12.30 Using Integer Linear Programming for Content Selection, Lexicalization, and Aggregation to Produce Compact Texts from OWL Ontologies Gerasimos Lampouras and Ion Androutsopoulos

12.30 – 14.00 Lunch

Session 3: Referring Expressions and Multimodality

14.00 – 14.30 Generating and Interpreting Referring Expressions as Belief State Planning and Plan Recognition Dustin Smith and Henry Lieberman

14.30 – 15.00 Graphs and Spatial Relations in the Generation of Referring Expressions Jette Viethen, Margaret Mitchell and Emiel Krahmer

79

Workshop 2: UZH in BioNLP 2013Fabio Rinaldi, Gerold Schneider, Simon Clematide, Tilia Ellendorff, Gintare Grigonyte and Don Tuggener

A Hybrid Approach for Biomedical Event ExtractionXuan Quang Pham, Minh Quang Le and Bao Quoc Ho

Identification of Genia Events using Multiple ClassifiersRoland Roller and Mark Stevenson

Exploring a Probabilistic Earley Parser for Event Composition in Biomedical TextsMai-Vu Tran, Nigel Collier, Hoang-Quynh Le, Van-Thuy Phi and Thanh-Binh Pham

Detecting Relations in the Gene Regulation NetworkThomas Provoost and Marie-Francine Moens

Ontology-based Semantic Annotation: an Automatic Hybrid Rule-based MethodSondes Bannour, Laurent Audibert and Henry Soldano

Building A Contrasting Taxa Extractor for Relation Identification from Assertions: BIOlogical Taxonomy & Ontology Phrase Extraction SystemCyril Grouin

Guest announcement:The BioASQ Project and ChallengesIon Androutsopoulos

15.30-16.00 Break

Session 4: Oral Presentations: Bacteria: Gene Regulation Network and Biotope

16.00 – 16.10 BioNLP Shared Task 2013 – An Overview of the Genic Regulation Network Task Robert Bossy, Philippe Bessières and Claire Nédellec

16.10 – 16. 20 BioNLP shared Task 2013 – An Overview of the Bacteria Biotope Task Robert Bossy, Wiktoria Golik, Zorana Ratkovic, Philippe Bessières and Claire Nédellec

16.20 – 16.40 Bacteria Biotope Detection, Ontology-based Normalization, and Relation Extraction using Syntactic Rules Ilknur Karadeniz and Arzucan Özgür

16.40 – 17.00 Extracting Gene Regulation Networks Using Linear-Chain Conditional Random Fields and Rules Slavko Zitnik, Marinka Žitnik, Blaž Zupan and Marko Bajec

17.00 – 17.30 IRISA participation to BioNLP-ST13: Information Extraction Tasks Lazy-learning and Information Retrieval for Information Extraction Tasks Vincent Claveau

17.30 – 18.00 Session 5: General Discussion

78


ENLG 2013: 14th European Workshop on Natural Language Generationth thThursday, Friday, August 8 -9 , 2013 → Hall 1.7



Session 1: NLG from Semantic Representations and Knowledge Bases

9.00 – 9.30 Aligning Formal Meaning Representations with Surface Strings for Wide-Coverage Text Generation Valerio Basile and Johan Bos

9.30 – 10.00 Exploiting Ontology Lexica for Generating Natural Language Texts from RDF Data Philipp Cimiano, Janna Lüker, David Nagel and Christina Unger

10.00 – 10.30 User-Controlled, Robust Natural Language Generation from an Evolving Knowledge Base Eva Banik, Eric Kow and Vinay Chaudhri


Session 2: Realisation, Aggregation and Variation

11.00 – 11.30 Enhancing the Expression of Contrast in the SPaRKy Restaurant Corpus David Howcroft, Crystal Nakatsu and Michael White

11.30 – 12.00 Generating Elliptic Coordination Claire Gardent and Shashi Narayan

12.00 – 12.30 Using Integer Linear Programming for Content Selection, Lexicalization, and Aggregation to Produce Compact Texts from OWL Ontologies Gerasimos Lampouras and Ion Androutsopoulos

12.30 – 14.00 Lunch

Session 3: Referring Expressions and Multimodality

14.00 – 14.30 Generating and Interpreting Referring Expressions as Belief State Planning and Plan Recognition Dustin Smith and Henry Lieberman

14.30 – 15.00 Graphs and Spatial Relations in the Generation of Referring Expressions Jette Viethen, Margaret Mitchell and Emiel Krahmer

79

Workshop 2: UZH in BioNLP 2013Fabio Rinaldi, Gerold Schneider, Simon Clematide, Tilia Ellendorff,

78


Regular Posters

Automatic Voice Selection in Japanese based on Various Linguistic InformationRyu Iida and Takenobu TokunagaMIME - NLG in Pre-Hospital CareAnne Schneider, Alasdair Mort, Chris Mellish, Ehud Reiter, Phil Wilson and Pierre-Luc Vaudry

Generation of Quantified Referring Expressions: Evidence from Experimental DataDale Barr, Kees van Deemter and Raquel Fernandez

POS-Tag Based Poetry Generation with WordNetManex Agirrezabal, Bertol Arrieta, Aitzol Astigarraga and Mans Hulden

Greetings Generation in Video Role Playing GamesBjörn Schlünder and Ralf Klabunde

On the Feasibility of Automatically Describing n-dimensional ObjectsPablo Duboue

GenNext: A Consolidated Domain Adaptable NLG SystemFrank Schilder, Blake Howald and Ravi Kondadadi

Adapting SimpleNLG for Bilingual English-French RealisationPierre-Luc Vaudry and Guy Lapalme

A Case Study Towards Turkish Paraphrase AlignmentSeniz Demir, Ilknur Durgar El-Kahlout and Erdem Unal

Towards NLG for Physiological Data Monitoring with Body Area NetworksHadi Banaee, Mobyen Uddin Ahmed and Amy Loutfi

Demos

MIME- NLG Support for Complex and Unstable Pre-hospital EmergenciesAnne Schneider, Alasdair Mort, Chris Mellish, Ehud Reiter, Phil Wilson and Pierre-Luc Vaudry

Thoughtland: Natural Language Descriptions for Machine Learning n-dimensional Error FunctionsPablo Duboue

Generation Challenges Posters

An Automatic Method for Building a Data-to-Text GeneratorSina Zarriess and Kyle Richardson

LOR-KBGEN, A Hybrid Approach To Generating from the KBGen Knowledge-BaseBikash Gyawali and Claire Gardent

Team UDEL KBGen 2013 ChallengeKeith Butler, Priscilla Moraes, Ian Tabolt and Kathy McCoy

Content Selection Challenge - University of Aberdeen EntryRoman Kutlak, Chris Mellish and Kees van Deemter

UIC-CSC: The Content Selection Challenge Entry from the University of Illinois at ChicagoHareen Venigalla and Barbara Di Eugenio

81

15.00 – 15.30 What and Where: An Empirical Investigation of Pointing Gestures and Descriptions in Multimodal Referring Actions Albert Gatt and Patrizia Paggio


16.00 – 17.00 Invited Talk I: Natural Language Generation and Summarization at RALI Guy Lapalme

17.00 – 18.30 Round Table Discussion Convergences and divergences in generation from data, text, and conceptual input

thFriday, August 9 , 2013

9.00 – 10.00 Invited Talk II: Narrative Composition: Achieving the Perceived Linearity of Narrative Pablo Gervás

Session 4: NLG for Learner Support

10.00 – 10.30 Generating Natural Language Questions to Support Learning On-Line David Lindberg, Fred Popowich, John Nesbit and Phil Winne


11.00 – 11.30 Generating Student Feedback from Time-Series Data Using Reinforcement Learning Dimitra Gkatzia, Helen Hastie, Srinivasan Janarthanam and Oliver Lemon

Generation Challenges

11.30 – 12.00 The KBGen Challenge Eva Banik, Claire Gardent and Eric Kow

12.00 – 12.30 Overview of the First Content Selection Challenge from Open Semantic Web Data Nadjet Bouayad-Agha, Gerard Casamayor, Leo Wanner and Chris Mellish

12.30 – 14.00 Lunch

14.00 – 15.30 Poster Session


Session 5: NLG from Textual Input

16.00 – 16.30 Deconstructing Human Literature Reviews – A Framework for Multi-Document Summarization Kokil Jaidka, Christopher Khoo and Jin-Cheon Na

16.30 – 17.00 Abstractive Meeting Summarization with Entailment and Fusion Yashar Mehdad, Giuseppe Carenini, Frank Tompa and Raymond T. Ng

17.00 – 17.15 Conclusion

WORKSHOP 2

80

Regular Posters

Automatic Voice Selection in Japanese based on Various Linguistic InformationRyu Iida and Takenobu TokunagaMIME - NLG in Pre-Hospital CareAnne Schneider, Alasdair Mort, Chris Mellish, Ehud Reiter, Phil Wilson and Pierre-Luc Vaudry

Generation of Quantified Referring Expressions: Evidence from Experimental DataDale Barr, Kees van Deemter and Raquel Fernandez

POS-Tag Based Poetry Generation with WordNetManex Agirrezabal, Bertol Arrieta, Aitzol Astigarraga and Mans Hulden

Greetings Generation in Video Role Playing GamesBjörn Schlünder and Ralf Klabunde

On the Feasibility of Automatically Describing n-dimensional ObjectsPablo Duboue

GenNext: A Consolidated Domain Adaptable NLG SystemFrank Schilder, Blake Howald and Ravi Kondadadi

Adapting SimpleNLG for Bilingual English-French RealisationPierre-Luc Vaudry and Guy Lapalme

A Case Study Towards Turkish Paraphrase AlignmentSeniz Demir, Ilknur Durgar El-Kahlout and Erdem Unal

Towards NLG for Physiological Data Monitoring with Body Area NetworksHadi Banaee, Mobyen Uddin Ahmed and Amy Loutfi

Demos

MIME- NLG Support for Complex and Unstable Pre-hospital EmergenciesAnne Schneider, Alasdair Mort, Chris Mellish, Ehud Reiter, Phil Wilson and Pierre-Luc Vaudry

Thoughtland: Natural Language Descriptions for Machine Learning n-dimensional Error FunctionsPablo Duboue

Generation Challenges Posters

An Automatic Method for Building a Data-to-Text GeneratorSina Zarriess and Kyle Richardson

LOR-KBGEN, A Hybrid Approach To Generating from the KBGen Knowledge-BaseBikash Gyawali and Claire Gardent

Team UDEL KBGen 2013 ChallengeKeith Butler, Priscilla Moraes, Ian Tabolt and Kathy McCoy

Content Selection Challenge - University of Aberdeen EntryRoman Kutlak, Chris Mellish and Kees van Deemter

UIC-CSC: The Content Selection Challenge Entry from the University of Illinois at ChicagoHareen Venigalla and Barbara Di Eugenio

81

15.00 – 15.30 What and Where: An Empirical Investigation of Pointing Gestures and Descriptions in Multimodal Referring Actions Albert Gatt and Patrizia Paggio


16.00 – 17.00 Invited Talk I: Natural Language Generation and Summarization at RALI Guy Lapalme

17.00 – 18.30 Round Table Discussion Convergences and divergences in generation from data, text, and conceptual input


9.00 – 10.00 Invited Talk II: Narrative Composition: Achieving the Perceived Linearity of Narrative Pablo Gervás

Session 4: NLG for Learner Support

10.00 – 10.30 Generating Natural Language Questions to Support Learning On-Line David Lindberg, Fred Popowich, John Nesbit and Phil Winne


11.00 – 11.30 Generating Student Feedback from Time-Series Data Using Reinforcement Learning Dimitra Gkatzia, Helen Hastie, Srinivasan Janarthanam and Oliver Lemon

Generation Challenges

11.30 – 12.00 The KBGen Challenge Eva Banik, Claire Gardent and Eric Kow

12.00 – 12.30 Overview of the First Content Selection Challenge from Open Semantic Web Data Nadjet Bouayad-Agha, Gerard Casamayor, Leo Wanner and Chris Mellish

12.30 – 14.00 Lunch

14.00 – 15.30 Poster Session


Session 5: NLG from Textual Input

16.00 – 16.30 Deconstructing Human Literature Reviews – A Framework for Multi-Document Summarization Kokil Jaidka, Christopher Khoo and Jin-Cheon Na

16.30 – 17.00 Abstractive Meeting Summarization with Entailment and Fusion Yashar Mehdad, Giuseppe Carenini, Frank Tompa and Raymond T. Ng

17.00 – 17.15 Conclusion

WORKSHOP 2

80

Yandex School of Data Analysis Machine Translation Systems for WMT13Alexey Borisov, Jacob Dlougach and Irina Galinskaya The Karlsruhe Institute of Technology Translation Systems for the WMT 2013Eunah Cho, Thanh-Le Ha, Mohammed Mediani, Jan Niehues, Teresa Herrmann, Isabel Slawik and Alex Waibel

TÜBITAK-BILGEM German-English Machine Translation Systems for W13Ilknur Durgar El-Kahlout and Coşkun Mermer

Edinburgh's Machine Translation Systems for European Language PairsNadir Durrani, Barry Haddow, Kenneth Heafield and Philipp Koehn

Munich-Edinburgh-Stuttgart Submissions of OSM Systems at WMT13Nadir Durrani, Alexander Fraser, Helmut Schmid, Hassan Sajjad and Richárd Farkas

Towards Efficient Large-Scale Feature-Rich Statistical Machine TranslationVladimir Eidelman, Ke Wu, Ferhan Ture, Philip Resnik and Jimmy Lin

The TALP-UPC Phrase-Based Translation Systems for WMT13: System Combination with Morphology Generation, Domain Adaptation and Corpus FilteringLluís Formiga, Marta R. Costa-jussà, José B. Mariño, José A. R. Fonollosa, Alberto Barrón-Cedeño and Lluis Marquez

PhraseFix: Statistical Post-Editing of TectoMTPetra Galuščáková, Martin Popel and Ondřej Bojar

Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation TaskSpence Green, Daniel Cer, Kevin Reschke, Rob Voigt, John Bauer, Sida Wang, Natalia Silveira, Julia Neidert and Christopher D. Manning

Factored Machine Translation Systems for Russian-EnglishStéphane Huet, Elena Manishina and Fabrice Lefèvre

Omnifluent English-to-French and Russian-to-English Systems for the 2013 Workshop on Statistical Machine TranslationEvgeny Matusov and Gregor Leusch Pre-Reordering for Machine Translation Using Transition-Based Walks on Dependency Parse TreesAntonio Valerio Miceli Barone and Giuseppe Attardi

Edinburgh's Syntax-Based Machine Translation SystemsMaria Nadejde, Philip Williams and Philipp Koehn

Shallow Semantically-Informed PBSMT and HPBSMTTsuyoshi Okita, Qun Liu and Josef van Genabith Joint WMT 2013 Submission of the QUAERO ProjectStephan Peitz, Saab Mansour, Matthias Huck, Markus Freitag, Hermann Ney, Eunah Cho, Teresa Herrmann, Mohammed Mediani, Jan Niehues, Alex Waibel, Alexander Allauzen, Quoc Khanh Do, Bianka Buschbeck and Tonio Wandmacher

83

thWMT 2013: 8 Workshop on Statistical Machine Translationth thThursday, Friday, August 8 -9 , 2013 → Hall 8



Session 1: Shared Tasks and Their Evaluation

9.10 – 10.10 Findings of the 2013 Workshop on Statistical Machine Translation Ondřej Bojar, Christian Buck, Chris Callison-Burch, Christian Federmann, Barry Haddow, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut and Lucia Specia

Results of the WMT13 Metrics Shared Task Matouš Macháček and Ondřej Bojar

10.10 – 10.30 The Feasibility of HMEANT as a Human MT Evaluation Metric Alexandra Birch, Barry Haddow, Ulrich Germann, Maria Nadejde, Christian Buck and Philipp Koehn

10.30 – 11.00 Coffee

Session 2: Poster Session

11.00 – 12.30 Shared Task: Translation

LIMSI @ WMT13 Alexander Allauzen, Nicolas Pécheux, Quoc Khanh Do, Marco Dinarelli, Thomas Lavergne, Aurélien Max, Hai-Son Le and François Yvon The CMU Machine Translation Systems at WMT 2013: Syntax, Synthetic Translation Options, and Pseudo-ReferencesWaleed Ammar, Victor Chahuneau, Michael Denkowski, Greg Hanneman, Wang Ling, Austin Matthews, Kenton Murray, Nicola Segall, Alon Lavie and Chris Dyer

Feature Decay Algorithms for Fast Deployment of Accurate Statistical Machine Translation SystemsErgun Bicici

CUni Multilingual Matrix in the WMT 2013 Shared TaskKarel Bílek and Daniel Zeman

Chimera – Three Heads for English-to-Czech TranslationOndřej Bojar, Rudolf Rosa and Aleš Tamchyn

Workshop 3:

82


Yandex School of Data Analysis Machine Translation Systems for WMT13Alexey Borisov, Jacob Dlougach and Irina Galinskaya The Karlsruhe Institute of Technology Translation Systems for the WMT 2013Eunah Cho, Thanh-Le Ha, Mohammed Mediani, Jan Niehues, Teresa Herrmann, Isabel Slawik and Alex Waibel

TÜBITAK-BILGEM German-English Machine Translation Systems for W13Ilknur Durgar El-Kahlout and Coşkun Mermer

Edinburgh's Machine Translation Systems for European Language PairsNadir Durrani, Barry Haddow, Kenneth Heafield and Philipp Koehn

Munich-Edinburgh-Stuttgart Submissions of OSM Systems at WMT13Nadir Durrani, Alexander Fraser, Helmut Schmid, Hassan Sajjad and Richárd Farkas

Towards Efficient Large-Scale Feature-Rich Statistical Machine TranslationVladimir Eidelman, Ke Wu, Ferhan Ture, Philip Resnik and Jimmy Lin

The TALP-UPC Phrase-Based Translation Systems for WMT13: System Combination with Morphology Generation, Domain Adaptation and Corpus FilteringLluís Formiga, Marta R. Costa-jussà, José B. Mariño, José A. R. Fonollosa, Alberto Barrón-Cedeño and Lluis Marquez

PhraseFix: Statistical Post-Editing of TectoMTPetra Galuščáková, Martin Popel and Ondřej Bojar

Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation TaskSpence Green, Daniel Cer, Kevin Reschke, Rob Voigt, John Bauer, Sida Wang, Natalia Silveira, Julia Neidert and Christopher D. Manning

Factored Machine Translation Systems for Russian-EnglishStéphane Huet, Elena Manishina and Fabrice Lefèvre

Omnifluent English-to-French and Russian-to-English Systems for the 2013 Workshop on Statistical Machine TranslationEvgeny Matusov and Gregor Leusch Pre-Reordering for Machine Translation Using Transition-Based Walks on Dependency Parse TreesAntonio Valerio Miceli Barone and Giuseppe Attardi

Edinburgh's Syntax-Based Machine Translation SystemsMaria Nadejde, Philip Williams and Philipp Koehn

Shallow Semantically-Informed PBSMT and HPBSMTTsuyoshi Okita, Qun Liu and Josef van Genabith Joint WMT 2013 Submission of the QUAERO ProjectStephan Peitz, Saab Mansour, Matthias Huck, Markus Freitag, Hermann Ney, Eunah Cho, Teresa Herrmann, Mohammed Mediani, Jan Niehues, Alex Waibel, Alexander Allauzen, Quoc Khanh Do, Bianka Buschbeck and Tonio Wandmacher

83

thWMT 2013: 8 Workshop on Statistical Machine Translationth thThursday, Friday, August 8 -9 , 2013 → Hall 8



Session 1: Shared Tasks and Their Evaluation

9.10 – 10.10 Findings of the 2013 Workshop on Statistical Machine Translation Ondřej Bojar, Christian Buck, Chris Callison-Burch, Christian Federmann, Barry Haddow, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut and Lucia Specia

Results of the WMT13 Metrics Shared Task Matouš Macháček and Ondřej Bojar

10.10 – 10.30 The Feasibility of HMEANT as a Human MT Evaluation Metric Alexandra Birch, Barry Haddow, Ulrich Germann, Maria Nadejde, Christian Buck and Philipp Koehn

10.30 – 11.00 Coffee


11.00 – 12.30 Shared Task: Translation

LIMSI @ WMT13 Alexander Allauzen, Nicolas Pécheux, Quoc Khanh Do, Marco Dinarelli, Thomas Lavergne, Aurélien Max, Hai-Son Le and François Yvon The CMU Machine Translation Systems at WMT 2013: Syntax, Synthetic Translation Options, and Pseudo-ReferencesWaleed Ammar, Victor Chahuneau, Michael Denkowski, Greg Hanneman, Wang Ling, Austin Matthews, Kenton Murray, Nicola Segall, Alon Lavie and Chris Dyer

Feature Decay Algorithms for Fast Deployment of Accurate Statistical Machine Translation SystemsErgun Bicici

CUni Multilingual Matrix in the WMT 2013 Shared TaskKarel Bílek and Daniel Zeman

Chimera – Three Heads for English-to-Czech TranslationOndřej Bojar, Rudolf Rosa and Aleš Tamchyn

Workshop 3:

82



Session 6: Learning

9.00 – 9.20 Multi-Task Learning for Improved Discriminative Training in SMT Patrick Simianer and Stefan Riezler

9.20 – 9.40 Online Learning Approaches in Computer Assisted Translation Prashant Mathur, Cettolo Mauro and Marcello Federico

9.40 – 10.00 Length-Incremental Phrase Training for SMT Joern Wuebker and Hermann Ney

10.00 – 10.20 Positive Diversity Tuning for Machine Translation System Combination Daniel Cer, Christopher D. Manning and Dan Jurafsky



11.00 – 12.30 Shared Task: Quality Estimation

Selecting Feature Sets for Comparative and Time-Oriented Quality Estimation of Machine Translation OutputEleftherios Avramidis and Maja Popovic

SHEF-Lite: When Less is More for Translation Quality EstimationDaniel Beck, Kashif Shah, Trevor Cohn and Lucia Specia

Referential Translation Machines for Quality EstimationErgun Bicici

FBK-UEdin Participation to the WMT13 Quality Estimation Shared TaskJosé Guilherme Camargo de Souza, Christian Buck, Marco Turchi and Matteo Negri

The TALP-UPC Approach to System Selection: Asiya Features and Pairwise Classification Using Random ForestsLluís Formiga, Meritxell Gonzàlez, Alberto Barrón-Cedeño, José A. R. Fonollosa and Lluis Marquez

Quality Estimation for Machine Translation Using the Joint Method of E valuation Criteria and Statistical ModelingAaron Li-Feng Han, Yi Lu, Derek F. Wong, Lidia S. Chao, Liangye He and Junwen Xing

MT Quality Estimation: The CMU System for WMT'13Silja Hildebrand and Stephan Vogel

LORIA System for the WMT13 Quality Estimation Shared TaskDavid Langlois and Kamel Smaili

LIG System for WMT13 QE Task: Investigating the Usefulness of Features in Word Confidence Estimation for MTNgoc Quang Luong, Benjamin Lecouteux and Laurent Besacier

85

The RWTH Aachen Machine Translation System for WMT 2013Stephan Peitz, Saab Mansour, Jan-Thorsten Peter, Christoph Schmidt, Joern Wuebker, Matthias Huck, Markus Freitag and Hermann Ney

The University of Cambridge Russian-English System at WMT13Juan Pino, Aurelien Waite, Tong Xiao, Adrià de Gispert, Federico Flego and William Byrne Joshua 5.0: Sparser, Better, Faster, ServerMatt Post, Juri Ganitkevitch, Luke Orland, Jonathan Weese, Yuan Cao and Chris Callison-Burch The CNGL-DCU-Prompsit Translation Systems for WMT13Raphael Rubino, Antonio Toral, Santiago Cortés Vaíllo, Jun Xie, Xiaofeng Wu, Stephen Doherty and Qun Liu QCRI-MES Submission at WMT13: Using Transliteration Mining to Improve Statistical Machine TranslationHassan Sajjad, Svetlana Smekalova, Nadir Durrani, Alexander Fraser and Helmut Schmid

Tunable Distortion Limits and Corpus Cleaning for SMTSara Stymne, Christian Hardmeier, Jörg Tiedemann and Joakim Nivre

Munich-Edinburgh-Stuttgart Submissions at WMT13: Morphological and Syntactic Processing for SMTMarion Weller, Max Kisselew, Svetlana Smekalova, Alexander Fraser, Helmut Schmid, Nadir Durrani, Hassan Sajjad and Richárd Farkas


Session 3: Invited Talk

14.00 – 15.10 Andreas Eisele: MT@EC: Serving the multilingual needs of the European Commission

Session 4: Quality Estimation

15.10 – 15.30 Coping with the Subjectivity of Human Judgements in MT Quality Estimation Marco Turchi, Matteo Negri and Marcello Federico


Session 5: Translation Models

16.00 – 16.20 Online Polylingual Topic Models for Fast Document Translation Detection Kriste Krstovski and David A. Smith

16.20 – 16.40 Combining Bilingual and Comparable Corpora for Low Resource Machine Translation Ann Irvine and Chris Callison-Burch

16.40 – 17.00 Generating English Determiners in Phrase-Based Translation with Synthetic Translation Options Yulia Tsvetkov, Chris Dyer, Lori Levin and Archna Bhatia

17.00 – 17.20 Dramatically Reducing Training Data Size Through Vocabulary Saturation William Lewis and Sauleh Eetemadi

WORKSHOP 3

84


Session 6: Learning

9.00 – 9.20 Multi-Task Learning for Improved Discriminative Training in SMT Patrick Simianer and Stefan Riezler

9.20 – 9.40 Online Learning Approaches in Computer Assisted Translation Prashant Mathur, Cettolo Mauro and Marcello Federico

9.40 – 10.00 Length-Incremental Phrase Training for SMT Joern Wuebker and Hermann Ney

10.00 – 10.20 Positive Diversity Tuning for Machine Translation System Combination Daniel Cer, Christopher D. Manning and Dan Jurafsky



11.00 – 12.30 Shared Task: Quality Estimation

Selecting Feature Sets for Comparative and Time-Oriented Quality Estimation of Machine Translation OutputEleftherios Avramidis and Maja Popovic

SHEF-Lite: When Less is More for Translation Quality EstimationDaniel Beck, Kashif Shah, Trevor Cohn and Lucia Specia

Referential Translation Machines for Quality EstimationErgun Bicici

FBK-UEdin Participation to the WMT13 Quality Estimation Shared TaskJosé Guilherme Camargo de Souza, Christian Buck, Marco Turchi and Matteo Negri

The TALP-UPC Approach to System Selection: Asiya Features and Pairwise Classification Using Random ForestsLluís Formiga, Meritxell Gonzàlez, Alberto Barrón-Cedeño, José A. R. Fonollosa and Lluis Marquez

Quality Estimation for Machine Translation Using the Joint Method of E valuation Criteria and Statistical ModelingAaron Li-Feng Han, Yi Lu, Derek F. Wong, Lidia S. Chao, Liangye He and Junwen Xing

MT Quality Estimation: The CMU System for WMT'13Silja Hildebrand and Stephan Vogel

LORIA System for the WMT13 Quality Estimation Shared TaskDavid Langlois and Kamel Smaili

LIG System for WMT13 QE Task: Investigating the Usefulness of Features in Word Confidence Estimation for MTNgoc Quang Luong, Benjamin Lecouteux and Laurent Besacier

85

The RWTH Aachen Machine Translation System for WMT 2013Stephan Peitz, Saab Mansour, Jan-Thorsten Peter, Christoph Schmidt, Joern Wuebker, Matthias Huck, Markus Freitag and Hermann Ney

The University of Cambridge Russian-English System at WMT13Juan Pino, Aurelien Waite, Tong Xiao, Adrià de Gispert, Federico Flego and William Byrne Joshua 5.0: Sparser, Better, Faster, ServerMatt Post, Juri Ganitkevitch, Luke Orland, Jonathan Weese, Yuan Cao and Chris Callison-Burch The CNGL-DCU-Prompsit Translation Systems for WMT13Raphael Rubino, Antonio Toral, Santiago Cortés Vaíllo, Jun Xie, Xiaofeng Wu, Stephen Doherty and Qun Liu QCRI-MES Submission at WMT13: Using Transliteration Mining to Improve Statistical Machine TranslationHassan Sajjad, Svetlana Smekalova, Nadir Durrani, Alexander Fraser and Helmut Schmid

Tunable Distortion Limits and Corpus Cleaning for SMTSara Stymne, Christian Hardmeier, Jörg Tiedemann and Joakim Nivre

Munich-Edinburgh-Stuttgart Submissions at WMT13: Morphological and Syntactic Processing for SMTMarion Weller, Max Kisselew, Svetlana Smekalova, Alexander Fraser, Helmut Schmid, Nadir Durrani, Hassan Sajjad and Richárd Farkas


Session 3: Invited Talk

14.00 – 15.10 Andreas Eisele: MT@EC: Serving the multilingual needs of the European Commission

Session 4: Quality Estimation

15.10 – 15.30 Coping with the Subjectivity of Human Judgements in MT Quality Estimation Marco Turchi, Matteo Negri and Marcello Federico


Session 5: Translation Models

16.00 – 16.20 Online Polylingual Topic Models for Fast Document Translation Detection Kriste Krstovski and David A. Smith

16.20 – 16.40 Combining Bilingual and Comparable Corpora for Low Resource Machine Translation Ann Irvine and Chris Callison-Burch

16.40 – 17.00 Generating English Determiners in Phrase-Based Translation with Synthetic Translation Options Yulia Tsvetkov, Chris Dyer, Lori Levin and Archna Bhatia

17.00 – 17.20 Dramatically Reducing Training Data Size Through Vocabulary Saturation William Lewis and Sauleh Eetemadi

WORKSHOP 3

84

thLAW VII & ID: 7 Linguistic Annotation Workshop &

Interoperability with Discourseth thThursday, Friday, August 8 -9 , 2013 → Hall 3.1



Session 1.1: Sparse Annotations and Error Correction

9.00 – 9.40 Christopher Manning (invited talk): Improving the Linguistics of Linguistic Annotation: Opportunities and Limits

9.40 – 10.05 Automatic Correction and Extension of Morphological Annotations Ramy Eskander, Nizar Habash, Ann Bies, Seth Kulick and Mohamed Maamouri

10.05 – 10.30 POS Tagging for Historical Texts with Sparse Training Data Marcel Bollmann


Session 1.2: Comparison and Evaluation of Annotations

11.00 – 11.07 Utilizing State-of-the-art Parsers to Diagnose Problems in Treebank Annotation for a Less Resourced Language Quy Nguyen, Ngan Nguyen and Yusuke Miyao

11.07 – 11.14 Influence of Preprocessing on Dependency Syntax Annotation: Speed and Agreement Arne Skjaerholt

11.15 – 11.40 Continuous Measurement Scales in Human Evaluation of Machine Translation Yvette Graham, Timothy Baldwin, Alistair Moffat and Justin Zobel

11.40 – 12.05 Entailment: An Effective Metric for Comparing and Evaluating Hierarchical and Non-hierarchical Annotation Schemes Rohan Ramanath, Monojit Choudhury and Kalika Bali

12.05 – 12.30 A Framework for (Under)specifying Dependency Syntax without Overloading Annotators Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer and Jason Baldridge

12.30 – 14.00 Lunch

Workshop 4:

87

DCU-Symantec at the WMT 2013 Quality Estimation Shared TaskRaphael Rubino, Joachim Wagner, Jennifer Foster, Johann Roturier, Rasoul Samad Zadeh Kaljahi and Fred Hollowood

LIMSI Submission for the WMT'13 Quality Estimation Task: an Experiment with N-Gram PosteriorsAnil Kumar Singh, Guillaume Wisniewski and François Yvon

11.00 – 12.30 Shared Task: Evaluation

Ranking Translations using Error Analysis and Quality EstimationMark Fishel

Are ACT's Scores Increasing with Better Translation Quality?Najeh Hajlaoui

A Description of Tunable Machine Translation Evaluation Systems in WMT13 Metrics TaskAaron Li-Feng Han, Derek F. Wong, Lidia S. Chao, Yi Lu, Liangye He, Yiming Wang and Jiaji Zhou

MEANT at WMT 2013: A Tunable, Accurate yet Inexpensive Semantic Frame Based MT Evaluation MetricChi-kiu Lo and Dekai Wu

An Approach Using Style Classification Features for Quality EstimationErwan Moreau and Raphael Rubino

DCU Participation in WMT2013 Metrics TaskXiaofeng Wu, Hui Yu and Qun Liu


Session 8: Reordering and Hierarchical Models

14.00 – 14.20 Efficient Solutions for Word Reordering in German-English Phrase-Based Statistical Machine Translation Arianna Bisazza and Marcello Federico

14.20 – 14.40 A Phrase Orientation Model for Hierarchical Machine Translation Matthias Huck, Joern Wuebker, Felix Rietig and Hermann Ney

14.40 – 15.00 A Dependency-Constrained Hierarchical Model with Moses Yvette Graham

15.00 – 15.20 Investigations in Exact Inference for Hierarchical Translation Wilker Aziz, Marc Dymetman and Sriram Venkatapathy


Session 9: Alignment and Word Translation Models

16.00 – 16.20 Evaluating (and Improving) Sentence Alignment under Noisy Conditions Omar Zaidan and Vishal Chowdhary

16.20 – 16.40 Multi-Rate HMMs for Word Alignment Elif Eyigöz, Daniel Gildea and Kemal Oflazer

16.40 – 17.00 Hidden Markov Tree Model for Word Alignment Shuhei Kondo, Kevin Duh and Yuji Matsumoto

17.00 – 17.20 An MT Error-Driven Discriminative Word Lexicon using Sentence Structure Features Jan Niehues and Alex Waibel

86


thLAW VII & ID: 7 Linguistic Annotation Workshop &

Interoperability with Discourseth thThursday, Friday, August 8 -9 , 2013 → Hall 3.1



Session 1.1: Sparse Annotations and Error Correction

9.00 – 9.40 Christopher Manning (invited talk): Improving the Linguistics of Linguistic Annotation: Opportunities and Limits

9.40 – 10.05 Automatic Correction and Extension of Morphological Annotations Ramy Eskander, Nizar Habash, Ann Bies, Seth Kulick and Mohamed Maamouri

10.05 – 10.30 POS Tagging for Historical Texts with Sparse Training Data Marcel Bollmann


Session 1.2: Comparison and Evaluation of Annotations

11.00 – 11.07 Utilizing State-of-the-art Parsers to Diagnose Problems in Treebank Annotation for a Less Resourced Language Quy Nguyen, Ngan Nguyen and Yusuke Miyao

11.07 – 11.14 Influence of Preprocessing on Dependency Syntax Annotation: Speed and Agreement Arne Skjaerholt

11.15 – 11.40 Continuous Measurement Scales in Human Evaluation of Machine Translation Yvette Graham, Timothy Baldwin, Alistair Moffat and Justin Zobel

11.40 – 12.05 Entailment: An Effective Metric for Comparing and Evaluating Hierarchical and Non-hierarchical Annotation Schemes Rohan Ramanath, Monojit Choudhury and Kalika Bali

12.05 – 12.30 A Framework for (Under)specifying Dependency Syntax without Overloading Annotators Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer and Jason Baldridge

12.30 – 14.00 Lunch

Workshop 4:

87

DCU-Symantec at the WMT 2013 Quality Estimation Shared TaskRaphael Rubino, Joachim Wagner, Jennifer Foster, Johann Roturier, Rasoul Samad Zadeh Kaljahi and Fred Hollowood

LIMSI Submission for the WMT'13 Quality Estimation Task: an Experiment with N-Gram PosteriorsAnil Kumar Singh, Guillaume Wisniewski and François Yvon

11.00 – 12.30 Shared Task: Evaluation

Ranking Translations using Error Analysis and Quality EstimationMark Fishel

Are ACT's Scores Increasing with Better Translation Quality?Najeh Hajlaoui

A Description of Tunable Machine Translation Evaluation Systems in WMT13 Metrics TaskAaron Li-Feng Han, Derek F. Wong, Lidia S. Chao, Yi Lu, Liangye He, Yiming Wang and Jiaji Zhou

MEANT at WMT 2013: A Tunable, Accurate yet Inexpensive Semantic Frame Based MT Evaluation MetricChi-kiu Lo and Dekai Wu

An Approach Using Style Classification Features for Quality EstimationErwan Moreau and Raphael Rubino

DCU Participation in WMT2013 Metrics TaskXiaofeng Wu, Hui Yu and Qun Liu


Session 8: Reordering and Hierarchical Models

14.00 – 14.20 Efficient Solutions for Word Reordering in German-English Phrase-Based Statistical Machine Translation Arianna Bisazza and Marcello Federico

14.20 – 14.40 A Phrase Orientation Model for Hierarchical Machine Translation Matthias Huck, Joern Wuebker, Felix Rietig and Hermann Ney

14.40 – 15.00 A Dependency-Constrained Hierarchical Model with Moses Yvette Graham

15.00 – 15.20 Investigations in Exact Inference for Hierarchical Translation Wilker Aziz, Marc Dymetman and Sriram Venkatapathy


Session 9: Alignment and Word Translation Models

16.00 – 16.20 Evaluating (and Improving) Sentence Alignment under Noisy Conditions Omar Zaidan and Vishal Chowdhary

16.20 – 16.40 Multi-Rate HMMs for Word Alignment Elif Eyigöz, Daniel Gildea and Kemal Oflazer

16.40 – 17.00 Hidden Markov Tree Model for Word Alignment Shuhei Kondo, Kevin Duh and Yuji Matsumoto

17.00 – 17.20 An MT Error-Driven Discriminative Word Lexicon using Sentence Structure Features Jan Niehues and Alex Waibel

86


Session 2.2: Semantic Annotation

11.00 – 11.25 Relation Annotation for Understanding Research Papers Yuka Tateisi, Yo Shidahara, Yusuke Miyao and Akiko Aizawa

11.25 – 11.50 Developing Parallel Sense-tagged Corpora with Wordnets Francis Bond, Shan Wang, Eshley Huini Gao, Hazel Shuwen Mok and Jeanette Yiwen Tan

11.50 – 12.15 Animacy Annotation in the Hindi Treebank Itisree Jena, Riyaz Ahmad Bhat, Sambhav Jain and Dipti Misra Sharma

12.15 – 12.22 Automatic Named Entity Pre-annotation for Out-of-domain Human Annotation Sophie Rosset, Cyril Grouin, Thomas Lavergne, Mohamed Ben Jannet, Jérémy Leixa, Olivier Galibert and Pierre Zweigenbaum

12.22 – 12.29 Abstract Meaning Representation for Sembanking Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer and Nathan Schneider

12.30 – 14.00 Lunch

Session 2.3: Novel Methods in Annotation

14.00 – 14.25 The Benefits of a Model of Annotation Rebecca J. Passonneau and Bob Carpenter

14.25 – 14.50 Ranking the annotators: An agreement study on argumentation structure Andreas Peldszus and Manfred Stede

14.50 – 15.15 Leveraging Crowdsourcing for Paraphrase Recognition Martin Tschirsich and Gerold Hintz

15.15 – 15.40 Investigation of Annotator's Behaviour Using Eye-tracking Data Ryu Iida, Koh Mitsuda and Takenobu Tokunaga 15.40 – 16.00 Coffee break

Session 2.4: Further Discourse Papers; Posters and Demos

16.00 – 16.07 Enunciative and Modal Variations in Newswire Texts in French: From guideline to Automatic Annotation Marine Damiani and Delphine Battistelli

16.07 – 16.14 Annotating the Interaction between Focus and Modality: the Case of Exclusive Particles Amália Mendes, Iris Hendrickx, Agostinho Salgueiro and Luciana Ávila

16.15 – 17.15 Posters and Demos

17.15 – 17.30 Concluding Remarks

89

Session 1.3: Special Theme and Challenge – Interoperability and Discourse

14.00 – 14.25 Converting Italian Treebanks: Towards an Italian Stanford Dependency Treebank Cristina Bosco, Simonetta Montemagni and Maria Simi

14.25 – 14.50 Analyses of the Association between Discourse Relation and Sentiment Polarity with a Chinese Human-Annotated Corpus Hen-Hsen Huang, Chi-Hsin Yu, Tai-Wei Chang, Cong-Kai Lin and Hsin-Hsi Chen

14.50 – 15.15 LAW VII and ID Challenge Award: Towards a Better Understanding of Discourse: Integrating Multiple Discourse Annotation Perspectives Using UIMA Claudiu Mihăilă, Georgios Kontonatsios, Riza Theresa Batista-Navarro, Paul Thompson, Ioannis Korkontzelos and Sophia Ananiadou

15.15 – 15.22 Making UIMA Truly Interoperable with SPARQL Rafal Rak and Sophia Ananiadou

15.22 – 15.29 Importing MASC into the ANNIS Linguistic Database: A Case Study of Mapping GrAF Arne Neumann, Nancy Ide and Manfred Stede


Session 1.4: Shared Task

16.00 – 18.00 Introduction to the task and hands-on work (Maria Lakata and Sampo Pyysalo)

thAugust 9 , 2013

Session 2.1: Discourse Annotation

9.00 – 9.25 Generic Noun Phrases and Annotation of Coreference and Bridging Relations in the Prague Dependency Treebank Anna Nedoluzhko

9.25 – 9.50 Annotating Anaphoric Shell Nouns with their Antecedents Varada Kolhatkar, Heike Zinsmeister and Graeme Hirst

9.50 – 10.15 Applicative Structures and Immediate Discourse in the Turkish Discourse Bank Isin Demirsahin, Adnan Ozturel, Cem Bozsahin and Deniz Zeyrek

10.15 – 10.22 TURKSENT: A Sentiment Annotation Tool for Social Media Gülşen Eryiğit, Fatih Samet Çetin, Meltem Yanık, Tanel Temel and İlyas Çiçekli

10.22 – 10.29 Tweet Conversation Annotation Tool with a Focus on an Arabic Dialect, Moroccan Darija, Stephen Tratz, Douglas Briesch, Jamal Laoudi and Clare Voss


WORKSHOP 4

88

Session 2.2: Semantic Annotation

11.00 – 11.25 Relation Annotation for Understanding Research Papers Yuka Tateisi, Yo Shidahara, Yusuke Miyao and Akiko Aizawa

11.25 – 11.50 Developing Parallel Sense-tagged Corpora with Wordnets Francis Bond, Shan Wang, Eshley Huini Gao, Hazel Shuwen Mok and Jeanette Yiwen Tan

11.50 – 12.15 Animacy Annotation in the Hindi Treebank Itisree Jena, Riyaz Ahmad Bhat, Sambhav Jain and Dipti Misra Sharma

12.15 – 12.22 Automatic Named Entity Pre-annotation for Out-of-domain Human Annotation Sophie Rosset, Cyril Grouin, Thomas Lavergne, Mohamed Ben Jannet, Jérémy Leixa, Olivier Galibert and Pierre Zweigenbaum

12.22 – 12.29 Abstract Meaning Representation for Sembanking Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer and Nathan Schneider

12.30 – 14.00 Lunch

Session 2.3: Novel Methods in Annotation

14.00 – 14.25 The Benefits of a Model of Annotation Rebecca J. Passonneau and Bob Carpenter

14.25 – 14.50 Ranking the annotators: An agreement study on argumentation structure Andreas Peldszus and Manfred Stede

14.50 – 15.15 Leveraging Crowdsourcing for Paraphrase Recognition Martin Tschirsich and Gerold Hintz

15.15 – 15.40 Investigation of Annotator's Behaviour Using Eye-tracking Data Ryu Iida, Koh Mitsuda and Takenobu Tokunaga 15.40 – 16.00 Coffee break

Session 2.4: Further Discourse Papers; Posters and Demos

16.00 – 16.07 Enunciative and Modal Variations in Newswire Texts in French: From guideline to Automatic Annotation Marine Damiani and Delphine Battistelli

16.07 – 16.14 Annotating the Interaction between Focus and Modality: the Case of Exclusive Particles Amália Mendes, Iris Hendrickx, Agostinho Salgueiro and Luciana Ávila

16.15 – 17.15 Posters and Demos

17.15 – 17.30 Concluding Remarks

89

Session 1.3: Special Theme and Challenge – Interoperability and Discourse

14.00 – 14.25 Converting Italian Treebanks: Towards an Italian Stanford Dependency Treebank Cristina Bosco, Simonetta Montemagni and Maria Simi

14.25 – 14.50 Analyses of the Association between Discourse Relation and Sentiment Polarity with a Chinese Human-Annotated Corpus Hen-Hsen Huang, Chi-Hsin Yu, Tai-Wei Chang, Cong-Kai Lin and Hsin-Hsi Chen

14.50 – 15.15 LAW VII and ID Challenge Award: Towards a Better Understanding of Discourse: Integrating Multiple Discourse Annotation Perspectives Using UIMA Claudiu Mihăilă, Georgios Kontonatsios, Riza Theresa Batista-Navarro, Paul Thompson, Ioannis Korkontzelos and Sophia Ananiadou

15.15 – 15.22 Making UIMA Truly Interoperable with SPARQL Rafal Rak and Sophia Ananiadou

15.22 – 15.29 Importing MASC into the ANNIS Linguistic Database: A Case Study of Mapping GrAF Arne Neumann, Nancy Ide and Manfred Stede


Session 1.4: Shared Task

16.00 – 18.00 Introduction to the task and hands-on work (Maria Lakata and Sampo Pyysalo)

thAugust 9 , 2013

Session 2.1: Discourse Annotation

9.00 – 9.25 Generic Noun Phrases and Annotation of Coreference and Bridging Relations in the Prague Dependency Treebank Anna Nedoluzhko

9.25 – 9.50 Annotating Anaphoric Shell Nouns with their Antecedents Varada Kolhatkar, Heike Zinsmeister and Graeme Hirst

9.50 – 10.15 Applicative Structures and Immediate Discourse in the Turkish Discourse Bank Isin Demirsahin, Adnan Ozturel, Cem Bozsahin and Deniz Zeyrek

10.15 – 10.22 TURKSENT: A Sentiment Annotation Tool for Social Media Gülşen Eryiğit, Fatih Samet Çetin, Meltem Yanık, Tanel Temel and İlyas Çiçekli

10.22 – 10.29 Tweet Conversation Annotation Tool with a Focus on an Arabic Dialect, Moroccan Darija, Stephen Tratz, Douglas Briesch, Jamal Laoudi and Clare Voss


WORKSHOP 4

88

Session III: Cross-lingual methods and Machine Translation

15.10 – 15.30 Modernizing Historical Slovene Words with Character-based SMT Yves Scherrer and Tomaž Erjavec


16.00 – 16.25 Improving English-Russian Sentence Alignment through POS Tagging and Damerau Levenshtein Distance Andrey Kutuzov

16.25 – 16.50 Identifying False Friends between Closely Related Languages Nikola Ljubešic and Darja Fišer

16.50–17.15 Discussion: Establishing BSNLP SIG


Session IV: Information Extraction

9.20 – 9.45 Named Entity Recognition in Estonian Alexander Tkachenko, Timo Petmanson and Sven Laur

9.45–10.10 On Named Entity Recognition in Targeted Twitter Streams in Polish. Jakub Piskorski and Maud Ehrmann

10.10 – 10.30 Recognition of Named Entities Boundaries in Polish Texts Michał Marcinczuk and Jan Kocon


11.00 – 11.25 Adapting the PULS Event Extraction Framework to Analyze Russian Text Lidia Pivovarova, Mian Du and Roman Yangarber

11.25 – 11.50 Semi-automatic Acquisition of Lexical Resources and Grammars for Event Extraction in Bulgarian and Czech Hristo Tanev and Josef Steinberger

11.50 – 12.15 Wordnet-Based Cross-Language Identification of Semantic Relations Ivelina Stoyanova, Svetla Koeva and Svetlozara Leseva

12.15–12.30 Concluding Remarks

12.30 – 14.00 Lunch

91

thBSNLP 2013: 4 Biennial Workshop on Balto-Slavic

Natural Language Processingth thThursday, Friday, August 8 -9 , 2013 → Hall 3.2


9.00 – 9.15 Welcome Remarks

9.15 – 10.30 Invited Talk: Ontologies and Linked Open Data for Acquisition and Exploitation of Language Resources Kiril Simov


Session I: Opinion Mining and Sentiment Analysis

11.00 – 11.25 A Comparison of Approaches for Sentiment Classification on Lithuanian Internet Comments Jurgita Kapoceiut-Dzikiene , Algis Krupavicius and Tomas Krilavicius

11.25 – 11.45 Evaluating Sentiment Analysis Systems in Russian Ilia Chetviorkin and Natalia Loukachevitch

11.45 – 12.05 Aspect-Oriented Opinion Mining from User Reviews in Croatian Goran Glavaš, Damir Korencic and Jan Šnajder

Session II: Morphology, Syntax and Semantics

12.05 – 12.30 Frequently Asked Questions Retrieval for Croatian Based on Semantic Textual Similarity Mladen Karan, Lovro Žmak and Jan Šnajder

12.30 – 14.00 Lunch

14.00 – 14.25 Parsing Russian: a Hybrid Approach Dan Skatov, Sergey Liverko, Vladimir Okatiev and Dmitry Strebkov

14.25 – 14.45 GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts Marko Bekavac and Jan Šnajder

14.45 – 15.10 Lemmatization and Morphosyntactic Tagging of Croatian and Serbian Željko Agic, Nikola Ljubešic and Danijela Merkler

Workshop 5:

90


Session III: Cross-lingual methods and Machine Translation

15.10 – 15.30 Modernizing Historical Slovene Words with Character-based SMT Yves Scherrer and Tomaž Erjavec


16.00 – 16.25 Improving English-Russian Sentence Alignment through POS Tagging and Damerau Levenshtein Distance Andrey Kutuzov

16.25 – 16.50 Identifying False Friends between Closely Related Languages Nikola Ljubešic and Darja Fišer

16.50–17.15 Discussion: Establishing BSNLP SIG


Session IV: Information Extraction

9.20 – 9.45 Named Entity Recognition in Estonian Alexander Tkachenko, Timo Petmanson and Sven Laur

9.45–10.10 On Named Entity Recognition in Targeted Twitter Streams in Polish. Jakub Piskorski and Maud Ehrmann

10.10 – 10.30 Recognition of Named Entities Boundaries in Polish Texts Michał Marcinczuk and Jan Kocon


11.00 – 11.25 Adapting the PULS Event Extraction Framework to Analyze Russian Text Lidia Pivovarova, Mian Du and Roman Yangarber

11.25 – 11.50 Semi-automatic Acquisition of Lexical Resources and Grammars for Event Extraction in Bulgarian and Czech Hristo Tanev and Josef Steinberger

11.50 – 12.15 Wordnet-Based Cross-Language Identification of Semantic Relations Ivelina Stoyanova, Svetla Koeva and Svetlozara Leseva

12.15–12.30 Concluding Remarks

12.30 – 14.00 Lunch

91

thBSNLP 2013: 4 Biennial Workshop on Balto-Slavic

Natural Language Processingth thThursday, Friday, August 8 -9 , 2013 → Hall 3.2


9.00 – 9.15 Welcome Remarks

9.15 – 10.30 Invited Talk: Ontologies and Linked Open Data for Acquisition and Exploitation of Language Resources Kiril Simov


Session I: Opinion Mining and Sentiment Analysis

11.00 – 11.25 A Comparison of Approaches for Sentiment Classification on Lithuanian Internet Comments Jurgita Kapoceiut-Dzikiene , Algis Krupavicius and Tomas Krilavicius

11.25 – 11.45 Evaluating Sentiment Analysis Systems in Russian Ilia Chetviorkin and Natalia Loukachevitch

11.45 – 12.05 Aspect-Oriented Opinion Mining from User Reviews in Croatian Goran Glavaš, Damir Korencic and Jan Šnajder

Session II: Morphology, Syntax and Semantics

12.05 – 12.30 Frequently Asked Questions Retrieval for Croatian Based on Semantic Textual Similarity Mladen Karan, Lovro Žmak and Jan Šnajder

12.30 – 14.00 Lunch

14.00 – 14.25 Parsing Russian: a Hybrid Approach Dan Skatov, Sergey Liverko, Vladimir Okatiev and Dmitry Strebkov

14.25 – 14.45 GPKEX: Genetically Programmed Keyphrase Extraction from Croatian Texts Marko Bekavac and Jan Šnajder

14.45 – 15.10 Lemmatization and Morphosyntactic Tagging of Croatian and Serbian Željko Agic, Nikola Ljubešic and Danijela Merkler

Workshop 5:

90


15.04 – 15.07 Scientific Registers and Disciplinary Diversification: a Comparable Corpus Approach Elke Teich, Stefania Degaetano-Ortlieb, Hannah Kermes and Ekaterina Lapshinova-Koltunski

15.08 – 15.11 Improving MT System Using Extracted Parallel Fragments of Text from Comparable Corpora Rajdeep Gupta, Santanu Pal and Sivaji Bandyopadhyay

15.12 – 15.15 VARTRA: A Comparable Corpus for Analysis of Translation Variation Ekaterina Lapshinova-Koltunski

15.16 – 15.19 Building Ontologies from Collaborative Knowledge Bases to Search and Interpret Multilingual Corpora Yegin Genc, Elizabeth Lennon, Winter Mason and Jeffrey Nickerson

15.20 – 15.23 Using a Random Forest Classifier to Recognise Translations of Biomedical Terms acrossLanguages Georgios Kontonatsios, Ioannis Korkontzelos, Sophia Ananiadou and Jun'ichi Tsujii

15.24 – 15.27 Comparing Multilingual Comparable Articles Based On Opinions Motaz Saad, David Langlois and Kamel Smaili


Session: Comparable Corpora

16.00 – 16.30 Mining for Domain-specific Parallel Text from Wikipedia Magdalena Plamada and Martin Volk

16.30 – 17.00 Gathering and Generating Paraphrases from Twitter with Application to Normalization Wei Xu, Alan Ritter and Ralph Grishman

17.00 – 17.30 Learning Comparable Corpora from Latent Semantic Analysis Simplified Document Space Ekaterina Stambolieva

17.30 – 18.00 Chinese-Japanese Parallel Sentence Extraction from Quasi-Comparable Corpora Chenhui Chu, Toshiaki Nakazawa and Sadao Kurohashi

93

thBUCC 2013: 6 Workshop on Building and Using Comparable CorporathThursday, August 8 , 2013 → Hall 1.2

WORKSHOP PROGRAM:

Session: Invited Talk

9.00 – 10.00 Three Dimensions of Comparable Corpora: Same or Different Language, Given or Inferred Comparability, Means to an End or End in Itself Hinrich Schütze

Session: Terminology

10.00 – 10.30 Cross-lingual WSD for Translation Extraction from Comparable Corpora Marianna Apidianaki, Nikola Ljubešic and Darja Fišer


11.00 – 11.30 Bilingual Lexicon Extraction via Pivot Language and Word Alignment Tool Hong-seok Kwon, Hyeong-won Seo and Jae-hoon Kim

11.30 – 12.00 Using WordNet and Semantic Similarity for Bilingual Terminology Mining from Comparable Corpora Dhouha Bouamor, Nasredine Semmar and Pierre Zweigenbaum

12.00 – 12.30 A Comparison of Smoothing Techniques for Bilingual Lexicon Extraction from Comparable Corpora Amir Hazem and Emmanuel Morin


14.00 – 14.30 Finding More Bilingual Webpages with High Credibility via Link Analysis Chengzhi Zhang, Xuchen Yao and Chunyu Kit

14.30 – 15.00 A Modular Open-source Focused Crawler for Mining Monolingual and Bilingual Corpora from the Web Vassilis Papavassiliou, Prokopis Prokopidis and Gregor Thurmair

Session: Posters with Booster Session

15.00 – 15.03 Building Basic Vocabulary across 40 Languages Judit Acs, Katalin Pajkossy and Andras Kornai

Workshop 6:

92


15.04 – 15.07 Scientific Registers and Disciplinary Diversification: a Comparable Corpus Approach Elke Teich, Stefania Degaetano-Ortlieb, Hannah Kermes and Ekaterina Lapshinova-Koltunski

15.08 – 15.11 Improving MT System Using Extracted Parallel Fragments of Text from Comparable Corpora Rajdeep Gupta, Santanu Pal and Sivaji Bandyopadhyay

15.12 – 15.15 VARTRA: A Comparable Corpus for Analysis of Translation Variation Ekaterina Lapshinova-Koltunski

15.16 – 15.19 Building Ontologies from Collaborative Knowledge Bases to Search and Interpret Multilingual Corpora Yegin Genc, Elizabeth Lennon, Winter Mason and Jeffrey Nickerson

15.20 – 15.23 Using a Random Forest Classifier to Recognise Translations of Biomedical Terms acrossLanguages Georgios Kontonatsios, Ioannis Korkontzelos, Sophia Ananiadou and Jun'ichi Tsujii

15.24 – 15.27 Comparing Multilingual Comparable Articles Based On Opinions Motaz Saad, David Langlois and Kamel Smaili



16.00 – 16.30 Mining for Domain-specific Parallel Text from Wikipedia Magdalena Plamada and Martin Volk

16.30 – 17.00 Gathering and Generating Paraphrases from Twitter with Application to Normalization Wei Xu, Alan Ritter and Ralph Grishman

17.00 – 17.30 Learning Comparable Corpora from Latent Semantic Analysis Simplified Document Space Ekaterina Stambolieva

17.30 – 18.00 Chinese-Japanese Parallel Sentence Extraction from Quasi-Comparable Corpora Chenhui Chu, Toshiaki Nakazawa and Sadao Kurohashi

93

thBUCC 2013: 6 Workshop on Building and Using Comparable CorporathThursday, August 8 , 2013 → Hall 1.2

WORKSHOP PROGRAM:

Session: Invited Talk

9.00 – 10.00 Three Dimensions of Comparable Corpora: Same or Different Language, Given or Inferred Comparability, Means to an End or End in Itself Hinrich Schütze

Session: Terminology

10.00 – 10.30 Cross-lingual WSD for Translation Extraction from Comparable Corpora Marianna Apidianaki, Nikola Ljubešic and Darja Fišer


11.00 – 11.30 Bilingual Lexicon Extraction via Pivot Language and Word Alignment Tool Hong-seok Kwon, Hyeong-won Seo and Jae-hoon Kim

11.30 – 12.00 Using WordNet and Semantic Similarity for Bilingual Terminology Mining from Comparable Corpora Dhouha Bouamor, Nasredine Semmar and Pierre Zweigenbaum

12.00 – 12.30 A Comparison of Smoothing Techniques for Bilingual Lexicon Extraction from Comparable Corpora Amir Hazem and Emmanuel Morin


14.00 – 14.30 Finding More Bilingual Webpages with High Credibility via Link Analysis Chengzhi Zhang, Xuchen Yao and Chunyu Kit

14.30 – 15.00 A Modular Open-source Focused Crawler for Mining Monolingual and Bilingual Corpora from the Web Vassilis Papavassiliou, Prokopis Prokopidis and Gregor Thurmair

Session: Posters with Booster Session

15.00 – 15.03 Building Basic Vocabulary across 40 Languages Judit Acs, Katalin Pajkossy and Andras Kornai

Workshop 6:

92


Session 3: Semantics

14.00 – 14.30 The Semantic Augmentation of a Psycholinguistically-motivated Syntactic Formalism Asad Sayeed and Vera Demberg

14.30 – 15.00 Evaluating Neighbor Rank and Distance Measures as Predictors of Semantic Priming Gabriella Lapesa and Stefan Evert

15.00 – 15.30 Concreteness and Corpora: A Theoretical and Practical Study Felix Hill, Douwe Kiela and Anna Korhonen


Session 4: Discourse and Dialog

16.00 – 16.30 On the Information Conveyed by Discourse Markers Fatemeh Torabi Asr and Vera Demberg

16.30 – 17.00 Incremental Grammar Induction from Child-Directed Dialogue Utterances Arash Eshghi, Julian Hough and Matthew Purver

17.00 Invited Talk by Rick Lewis

95

Cognitive Modeling and Computational LinguisticsthThursday, August 8 , 2013 → Hall 10

WORKSHOP PROGRAM:


8.30 Invited Talk by Sharon Goldwater

Session 1: Segmentation and Phonetics

9.30 – 10.00 Why is English so Easy to Segment? Abdellah Fourtassi, Benjamin Börschinger, Mark Johnson and Emmanuel Dupoux

10.00 – 10.30 A Model of Generalization in Distributional Learning of Phonetic Categories Bozena Pajak, Klinton Bicknell and Roger Levy

10.30 Coffee Break

Session 2: Syntax and Morphology

11.00 – 11.30 Learning Non-concatenative Morphology Michelle Fullwood and Tim O'Donnell

11.30 – 12.00 Statistical Representation of Grammaticality Judgements: the Limits of N-Gram Models Alexander Clark, Gianluca Giorgolo and Shalom Lappin

12.00 – 2.30 An Analysis of Memory-based Processing Costs using Incremental Deep Syntactic Dependency Parsing Marten van Schijndel, Luan Nguyen and William Schuler

12.30 – 13.00 Computational Simulations of Second Language Construction Learning Yevgen Matusevych, Afra Alishahi and Ad Backus


Workshop 7:

94



14.00 – 14.30 The Semantic Augmentation of a Psycholinguistically-motivated Syntactic Formalism Asad Sayeed and Vera Demberg

14.30 – 15.00 Evaluating Neighbor Rank and Distance Measures as Predictors of Semantic Priming Gabriella Lapesa and Stefan Evert

15.00 – 15.30 Concreteness and Corpora: A Theoretical and Practical Study Felix Hill, Douwe Kiela and Anna Korhonen


Session 4: Discourse and Dialog

16.00 – 16.30 On the Information Conveyed by Discourse Markers Fatemeh Torabi Asr and Vera Demberg

16.30 – 17.00 Incremental Grammar Induction from Child-Directed Dialogue Utterances Arash Eshghi, Julian Hough and Matthew Purver

17.00 Invited Talk by Rick Lewis

95

Cognitive Modeling and Computational LinguisticsthThursday, August 8 , 2013 → Hall 10

WORKSHOP PROGRAM:


8.30 Invited Talk by Sharon Goldwater

Session 1: Segmentation and Phonetics

9.30 – 10.00 Why is English so Easy to Segment? Abdellah Fourtassi, Benjamin Börschinger, Mark Johnson and Emmanuel Dupoux

10.00 – 10.30 A Model of Generalization in Distributional Learning of Phonetic Categories Bozena Pajak, Klinton Bicknell and Roger Levy

10.30 Coffee Break

Session 2: Syntax and Morphology

11.00 – 11.30 Learning Non-concatenative Morphology Michelle Fullwood and Tim O'Donnell

11.30 – 12.00 Statistical Representation of Grammaticality Judgements: the Limits of N-Gram Models Alexander Clark, Gianluca Giorgolo and Shalom Lappin

12.00 – 2.30 An Analysis of Memory-based Processing Costs using Incremental Deep Syntactic Dependency Parsing Marten van Schijndel, Luan Nguyen and William Schuler

12.30 – 13.00 Computational Simulations of Second Language Construction Learning Yevgen Matusevych, Afra Alishahi and Ad Backus


Workshop 7:

94


14.00 – 14.20 Towards a Tool for Interactive Concept Building for Large Scale Analysis in the Humanities Andre Blessing, Jonathan Sonntag, Fritz Kliche, Ulrich Heid, Jonas Kuhn and Man- fred Stede 14.20 – 14.40 Learning to Extract Folktale Keywords Dolf Trieschnigg, Dong Nguyen and Mariët Theune

14.40 – 15.00 Towards Creating Precision Grammars from Interlinear Glossed Text: Inferring Large- Scale Typological Properties Emily M. Bender, Michael Wayne Goodman, Joshua Crowgey and Fei Xia

15.00 – 15.15 Using Comparable Collections of Historical Texts for Building a Diachronic Dictionary for Spelling Normalization Marilisa Amoia and José Manuel Martínez

15.15 –15.30 The (Un)faithful Machine Translator Ruth Jones and Ann Irvine

15.30 –16.00 Coffee Break

16.00 – 16.15 Integration of the Thesaurus for the Social Sciences (TheSoz) in an Information Extraction System Thierry Declerck

16.15 – 16.30 Temporal Classification for Historical Romanian Texts Alina Maria Ciobanu, Anca Dinu, Liviu Dinu, Vlad Niculae and Octavia-Maria Şulea

16.30 – 16.50 Multilingual Access to Cultural Heritage Content on the Semantic Web Dana Dannélls, Aarne Ranta, Ramona Enache, Mariana Damova and Maria Mateva

16.50 – 17.00 Closing

97

LaTeCH 2013: Language Technology for Cultural Heritage, Social

Sciences, and HumanitiesthThursday, August 8 , 2013 → Hall 4

WORKSHOP PROGRAM:

9.00 – 9.15 Welcome

9.15 – 9.35 Generating Paths through Cultural Heritage Collections Samuel Fernando, Paula Goodale, Paul Clough, Mark Stevenson, Mark Hall and Eneko Agirre

9.35 – 9.55 Using Character Overlap to Improve Language Transformation Sander Wubben, Emiel Krahmer and Antal van den Bosch

9.55 – 10.15 Comparison Between Historical Population Archives and Decentralized Databases Marijn Schraagen and Dionysius Huijsmans

10.15 – 10.30 Semi-automatic Construction of Cross-period Thesaurus Chaya Liebeskind, Ido Dagan and Jonathan Schler


11.00 – 11.15 Language Technology for Agile Social Media Science Simon Wibberley, David Weir and Jeremy Reffin

11.15 – 11.30 Morphological Annotation of Old and Middle Hungarian corpora Attila Novak, György Orosz and Nóra Wenszky

11.30 – 11.45 Argument Extraction for Supporting Public Policy Formulation Eirini Florou, Stasinos Konstantopoulos, Antonis Koukourikos and Pythagoras Karampiperis

11.45 – 12.30 SIGHUM annual business meeting


Workshop 8:

96


14.00 – 14.20 Towards a Tool for Interactive Concept Building for Large Scale Analysis in the Humanities Andre Blessing, Jonathan Sonntag, Fritz Kliche, Ulrich Heid, Jonas Kuhn and Man- fred Stede 14.20 – 14.40 Learning to Extract Folktale Keywords Dolf Trieschnigg, Dong Nguyen and Mariët Theune

14.40 – 15.00 Towards Creating Precision Grammars from Interlinear Glossed Text: Inferring Large- Scale Typological Properties Emily M. Bender, Michael Wayne Goodman, Joshua Crowgey and Fei Xia

15.00 – 15.15 Using Comparable Collections of Historical Texts for Building a Diachronic Dictionary for Spelling Normalization Marilisa Amoia and José Manuel Martínez

15.15 –15.30 The (Un)faithful Machine Translator Ruth Jones and Ann Irvine

15.30 –16.00 Coffee Break

16.00 – 16.15 Integration of the Thesaurus for the Social Sciences (TheSoz) in an Information Extraction System Thierry Declerck

16.15 – 16.30 Temporal Classification for Historical Romanian Texts Alina Maria Ciobanu, Anca Dinu, Liviu Dinu, Vlad Niculae and Octavia-Maria Şulea

16.30 – 16.50 Multilingual Access to Cultural Heritage Content on the Semantic Web Dana Dannélls, Aarne Ranta, Ramona Enache, Mariana Damova and Maria Mateva

16.50 – 17.00 Closing

97

LaTeCH 2013: Language Technology for Cultural Heritage, Social

Sciences, and HumanitiesthThursday, August 8 , 2013 → Hall 4

WORKSHOP PROGRAM:

9.00 – 9.15 Welcome

9.15 – 9.35 Generating Paths through Cultural Heritage Collections Samuel Fernando, Paula Goodale, Paul Clough, Mark Stevenson, Mark Hall and Eneko Agirre

9.35 – 9.55 Using Character Overlap to Improve Language Transformation Sander Wubben, Emiel Krahmer and Antal van den Bosch

9.55 – 10.15 Comparison Between Historical Population Archives and Decentralized Databases Marijn Schraagen and Dionysius Huijsmans

10.15 – 10.30 Semi-automatic Construction of Cross-period Thesaurus Chaya Liebeskind, Ido Dagan and Jonathan Schler


11.00 – 11.15 Language Technology for Agile Social Media Science Simon Wibberley, David Weir and Jeremy Reffin

11.15 – 11.30 Morphological Annotation of Old and Middle Hungarian corpora Attila Novak, György Orosz and Nóra Wenszky

11.30 – 11.45 Argument Extraction for Supporting Public Policy Formulation Eirini Florou, Stasinos Konstantopoulos, Antonis Koukourikos and Pythagoras Karampiperis

11.45 – 12.30 SIGHUM annual business meeting


Workshop 8:

96


14.00 – 14.50 Keynote Speech 2: Controlled Ascent: Imbuing Statistical MT with Linguistic Knowledge William Lewis and Chris Quirk


14.50 – 15.15 Poster Booster Presentations

Unsupervised Transduction Grammar Induction via Minimum Description LengthMarkus Saers, Karteek Addanki and Dekai Wu

Integrating Morpho-syntactic Features in English-Arabic Statistical Machine TranslationInes Turki Khemakhem, Salma Jamoussi and Abdelmajid Ben Hamadou

Experiments with POS-based Restructuring and Alignment-based Reordering for Statistical Machine TranslationShuo Li, Derek F. Wong and Lidia S. Chao

Building Bilingual Lexicon to Create Dialect Tunisian Corpora and Adapt Language ModelRahma Boujelbane, Mariem Ellouze khemekhem, Siwar BenAyed and Lamia Hadrich-Belguith

A Hybrid Word Alignment Model for Phrase-Based Statistical Machine TranslationSantanu Pal, Sudip Naskar and Sivaji Bandyopadhyay

15.30 – 16.00 Coffee Break (to occur concurrently with poster session)


16.00 – 16.25 Lexical Selection for Hybrid MT with Sequence Labeling Alex Rudnick and Michael Gasser

16.25 – 16.50 Two Approaches to Correcting Homophone Confusions in a Hybrid Machine Translation System Pierrette Bouillon, Johanna Gerlach, Ulrich Germann, Barry Haddow and Manny Rayner

Session 6: Multi-level Approaches

16.50 – 17.15 Uses of Monolingual In-Domain Corpora for Cross-Domain Adaptation with Hybrid MT Approaches An-Chang Hsieh, Hen-Hsen Huang and Hsin-Hsi Chen

17.15 – 17.40 Language-independent Hybrid MT with PRESEMT George Tambouratzis, Sokratis Sofianopoulos and Marina Vassiliou

17.40 – 17.50 Conclusions and Wrap-up Session

99

ndHYTRA 2013: 2 Workshop on Hybrid Approaches to TranslationthThursday, August 8 , 2013 → Hall 1.4

WORKSHOP PROGRAM:

8.50 – 9.00 Workshop Opening Workshop on Hybrid Approaches to Translation: Overview and Developments Marta Ruiz Costa-jussà, Rafael Banchs, Reinhard Rapp, Patrik Lambert, Kurt Eberle and Bogdan Babych

9.00 – 9.50 Keynote Speech 1: Statistical MT Systems Revisited: How much Hybridity do they have? Hermann Ney

Session 1: Morphology

9.50 – 10.15 Hybrid Selection of Language Model Training Data Using Linguistic Information and Perplexity Antonio Toral

10.15 – 10.40 Machine Learning Disambiguation of Quechua Verb Morphology Annette Rios Gonzales and Anne Göhring


Session 2: Syntax I

11.00 – 11.25 Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers Nathan Green and Zdenek Žabokrtský

11.25 – 11.50 Using Unlabeled Dependency Parsing for Pre-reordering for Chinese-to-Japanese Statistical Machine Translation Dan Han, Pascual Martinez-Gomez, Yusuke Miyao, Katsuhito Sudoh and Masaaki Nagata

Session 3: Syntax II

11.50 – 12.15 Reordering Rules for English-Hindi SMT Raj Nath Patel, Rohit Gupta, Prakash B. Pimpale and Sasikumar M

12.15 – 12.40 English to Hungarian Morpheme-based Statistical Machine Translation System with Reordering Rules László Laki, Attila Novak and Borbála Siklósi


Workshop 9:

98


14.00 – 14.50 Keynote Speech 2: Controlled Ascent: Imbuing Statistical MT with Linguistic Knowledge William Lewis and Chris Quirk


14.50 – 15.15 Poster Booster Presentations

Unsupervised Transduction Grammar Induction via Minimum Description LengthMarkus Saers, Karteek Addanki and Dekai Wu

Integrating Morpho-syntactic Features in English-Arabic Statistical Machine TranslationInes Turki Khemakhem, Salma Jamoussi and Abdelmajid Ben Hamadou

Experiments with POS-based Restructuring and Alignment-based Reordering for Statistical Machine TranslationShuo Li, Derek F. Wong and Lidia S. Chao

Building Bilingual Lexicon to Create Dialect Tunisian Corpora and Adapt Language ModelRahma Boujelbane, Mariem Ellouze khemekhem, Siwar BenAyed and Lamia Hadrich-Belguith

A Hybrid Word Alignment Model for Phrase-Based Statistical Machine TranslationSantanu Pal, Sudip Naskar and Sivaji Bandyopadhyay

15.30 – 16.00 Coffee Break (to occur concurrently with poster session)


16.00 – 16.25 Lexical Selection for Hybrid MT with Sequence Labeling Alex Rudnick and Michael Gasser

16.25 – 16.50 Two Approaches to Correcting Homophone Confusions in a Hybrid Machine Translation System Pierrette Bouillon, Johanna Gerlach, Ulrich Germann, Barry Haddow and Manny Rayner

Session 6: Multi-level Approaches

16.50 – 17.15 Uses of Monolingual In-Domain Corpora for Cross-Domain Adaptation with Hybrid MT Approaches An-Chang Hsieh, Hen-Hsen Huang and Hsin-Hsi Chen

17.15 – 17.40 Language-independent Hybrid MT with PRESEMT George Tambouratzis, Sokratis Sofianopoulos and Marina Vassiliou

17.40 – 17.50 Conclusions and Wrap-up Session

99

ndHYTRA 2013: 2 Workshop on Hybrid Approaches to TranslationthThursday, August 8 , 2013 → Hall 1.4

WORKSHOP PROGRAM:

8.50 – 9.00 Workshop Opening Workshop on Hybrid Approaches to Translation: Overview and Developments Marta Ruiz Costa-jussà, Rafael Banchs, Reinhard Rapp, Patrik Lambert, Kurt Eberle and Bogdan Babych

9.00 – 9.50 Keynote Speech 1: Statistical MT Systems Revisited: How much Hybridity do they have? Hermann Ney

Session 1: Morphology

9.50 – 10.15 Hybrid Selection of Language Model Training Data Using Linguistic Information and Perplexity Antonio Toral

10.15 – 10.40 Machine Learning Disambiguation of Quechua Verb Morphology Annette Rios Gonzales and Anne Göhring


Session 2: Syntax I

11.00 – 11.25 Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers Nathan Green and Zdenek Žabokrtský

11.25 – 11.50 Using Unlabeled Dependency Parsing for Pre-reordering for Chinese-to-Japanese Statistical Machine Translation Dan Han, Pascual Martinez-Gomez, Yusuke Miyao, Katsuhito Sudoh and Masaaki Nagata

Session 3: Syntax II

11.50 – 12.15 Reordering Rules for English-Hindi SMT Raj Nath Patel, Rohit Gupta, Prakash B. Pimpale and Sasikumar M

12.15 – 12.40 English to Hungarian Morpheme-based Statistical Machine Translation System with Reordering Rules László Laki, Attila Novak and Borbála Siklósi


Workshop 9:

98


Session 3: Presentations

14.00 – 14.20 Text Modification for Bulgarian Sign Language Users Slavina Lozanova, Ivelina Stoyanova, Svetlozara Leseva, Svetla Koeva and Boian Savtchev

14.20 – 14.40 Modeling Comma Placement in Chinese Text for Better Readability using Linguistic Features and Gaze Information Tadayoshi Hara, Chen Chen, Yoshinobu Kano and Akiko Aizawa

14.40 – 15.00 On The Applicability of Readability Models to Web Texts Sowmya Vajjala and Detmar Meurers

15.00 – 15.30 Report from NLP4ITA Horacio Saggion

15.30 – 16.00 Tea break Session 4: Presentations and Close

16.00 – 16.20 The CW Corpus: A New Resource for Evaluating the Identification of Complex Words Matthew Shardlow

16.20 – 16.40 A Pilot Study of Readability Prediction with Reading Time Hitoshi Nishikawa, Toshiro Makino and Yoshihiro Matsuo

16.40 Final Discussion and Close

101

ndPITR 2013: 2 Workshop on Predicting and Improving Text

Readability for Target Reader PopulationsthThursday, August 8 , 2013 → Hall 1.5

WORKSHOP PROGRAM:

9.20 – 10.30 Session 1: Plenary

9.20 Welcome and Introduction

9:30 Invited Talk: Identifying Outstanding Writing: Corpus and Experiments Based on the Science Journalism Genre Annie Louis 10.30 – 11.00 Coffee break 11.00 – 12.30 Session 2: Posters

11.00 Poster Teasers

11.20 Poster Session Sentence Simplification as Tree TransductionDan Feblowitz and David Kauchak

Building a German/Simple German Parallel Corpus for Automatic Text SimplificationDavid Klaper, Sarah Ebling, Martin Volk

The C-Score - Proposing Reading Comprehension Metrics as a Common Evaluation Measure for Text SimplificationIrina Temnikova and Galina Maneva

A Language-Independent Approach to Automatic Text Difficulty Assessment for Second-Language LearnersWade Shen, Jennifer Williams, Tamas Marius and Elizabeth Slesky

Guest Paper from NLP4ITA Proceedings:A System for the Simplification of Numerical Expressions at Different Levels of UnderstandabilitySusan Bautista, Raquel Hervás, Pablo Gervás, Richard Power and Sandra Williams


Workshop 10:

100


Session 3: Presentations

14.00 – 14.20 Text Modification for Bulgarian Sign Language Users Slavina Lozanova, Ivelina Stoyanova, Svetlozara Leseva, Svetla Koeva and Boian Savtchev

14.20 – 14.40 Modeling Comma Placement in Chinese Text for Better Readability using Linguistic Features and Gaze Information Tadayoshi Hara, Chen Chen, Yoshinobu Kano and Akiko Aizawa

14.40 – 15.00 On The Applicability of Readability Models to Web Texts Sowmya Vajjala and Detmar Meurers

15.00 – 15.30 Report from NLP4ITA Horacio Saggion

15.30 – 16.00 Tea break Session 4: Presentations and Close

16.00 – 16.20 The CW Corpus: A New Resource for Evaluating the Identification of Complex Words Matthew Shardlow

16.20 – 16.40 A Pilot Study of Readability Prediction with Reading Time Hitoshi Nishikawa, Toshiro Makino and Yoshihiro Matsuo

16.40 Final Discussion and Close

101

ndPITR 2013: 2 Workshop on Predicting and Improving Text

Readability for Target Reader PopulationsthThursday, August 8 , 2013 → Hall 1.5

WORKSHOP PROGRAM:

9.20 – 10.30 Session 1: Plenary

9.20 Welcome and Introduction

9:30 Invited Talk: Identifying Outstanding Writing: Corpus and Experiments Based on the Science Journalism Genre Annie Louis 10.30 – 11.00 Coffee break 11.00 – 12.30 Session 2: Posters

11.00 Poster Teasers

11.20 Poster Session Sentence Simplification as Tree TransductionDan Feblowitz and David Kauchak

Building a German/Simple German Parallel Corpus for Automatic Text SimplificationDavid Klaper, Sarah Ebling, Martin Volk

The C-Score - Proposing Reading Comprehension Metrics as a Common Evaluation Measure for Text SimplificationIrina Temnikova and Galina Maneva

A Language-Independent Approach to Automatic Text Difficulty Assessment for Second-Language LearnersWade Shen, Jennifer Williams, Tamas Marius and Elizabeth Slesky

Guest Paper from NLP4ITA Proceedings:A System for the Simplification of Numerical Expressions at Different Levels of UnderstandabilitySusan Bautista, Raquel Hervás, Pablo Gervás, Richard Power and Sandra Williams


Workshop 10:

100


Session 4

16.00 – 16.30 Investigating Connectivity and Consistency Criteria for Phrase Pair Extraction in Statistical Machine Translation Spyros Martzoukos, Christophe Costa Florêncio and Christof Monz

16.30 – 17.30 Grammars and Topic Models Mark Johnson

103

thMoL 2013: 13 Meeting on the Mathematics of LanguagethFriday, August 9 , 2013 → Hall 1.2

WORKSHOP PROGRAM:

Session 1

9.00 – 9.30 Distributions on Minimalist Grammar Derivations Tim Hunter and Chris Dyer

9.30 – 10.00 Order and Optionality: Minimalist Grammars with Adjunction Meaghan Fowlie

10.00 – 10.30 On the Parameterized Complexity of Linear Context-Free Rewriting Systems Martin Berglund, Henrik Björklund and Frank Drewes


Session 2

11.00 – 11.30 Segmenting Temporal Intervals for Tense and Aspect Tim Fernando

11.30 – 12.00 The Frobenius Anatomy of Relative Pronouns Stephen Clark, Bob Coecke and Mehrnoosh Sadrzadeh

12.00 – 12.30 Vowel Harmony and Subsequentiality Jeffrey Heinz and Regine Lai


Session 3

14.00 – 14.30 Learning Subregular Classes of Languages with Factored Deterministic Automata Jeffrey Heinz and Jim Rogers

14.30 – 15.00 Structure Learning in Weighted Languages Andras Kornai, Attila Zséder and Gábor Recski

15.00 – 15.30 Why Letter Substitution Puzzles are Not Hard to Solve: A Case Study in Entropy and Probabilistic Search-Complexity Eric Corlett and Gerald Penn


Workshop 11:

102


Session 4

16.00 – 16.30 Investigating Connectivity and Consistency Criteria for Phrase Pair Extraction in Statistical Machine Translation Spyros Martzoukos, Christophe Costa Florêncio and Christof Monz

16.30 – 17.30 Grammars and Topic Models Mark Johnson

103

thMoL 2013: 13 Meeting on the Mathematics of LanguagethFriday, August 9 , 2013 → Hall 1.2

WORKSHOP PROGRAM:

Session 1

9.00 – 9.30 Distributions on Minimalist Grammar Derivations Tim Hunter and Chris Dyer

9.30 – 10.00 Order and Optionality: Minimalist Grammars with Adjunction Meaghan Fowlie

10.00 – 10.30 On the Parameterized Complexity of Linear Context-Free Rewriting Systems Martin Berglund, Henrik Björklund and Frank Drewes


Session 2

11.00 – 11.30 Segmenting Temporal Intervals for Tense and Aspect Tim Fernando

11.30 – 12.00 The Frobenius Anatomy of Relative Pronouns Stephen Clark, Bob Coecke and Mehrnoosh Sadrzadeh

12.00 – 12.30 Vowel Harmony and Subsequentiality Jeffrey Heinz and Regine Lai


Session 3

14.00 – 14.30 Learning Subregular Classes of Languages with Factored Deterministic Automata Jeffrey Heinz and Jim Rogers

14.30 – 15.00 Structure Learning in Weighted Languages Andras Kornai, Attila Zséder and Gábor Recski

15.00 – 15.30 Why Letter Substitution Puzzles are Not Hard to Solve: A Case Study in Entropy and Probabilistic Search-Complexity Eric Corlett and Gerald Penn


Workshop 11:

102


15:00 – 15.30 Multilingual Summarization: Dimensionality Reduction and a Step Towards Optimal Term Coverage John Conroy, Sashka T. Davis, Jeff Kubina, Yi-Kai Liu, Dianne P. O'Leary, Judith D Schlesinger


16.00 – 16.20 Session 2 – Using a Keyness Metric for Single and Multi Document Summarisation Mahmoud El-Haj and Paul Rayson

Session 3: Single-document Summarization

16.20 – 16.40 Session 3 – Multilingual Summarization System Based on Analyzing the Discourse Structure at MultiLing 2013 Daniel Anechitei and Eugen Ignat

16.40 – 17.00 Session 3 – Multilingual Single-Document Summarization with MUSE Marina Litvak and Mark Last

17.00 Closing Discussion

105

MULTILING 2013: Multilingual Multi-Document SummarizationthFriday, August 9 , 2013 → Hall 1.4

WORKSHOP PROGRAM:

9.00 Introduction by the Organizers

Session 1: Data Contribution and Exploitation

9.05 – 9.35 Session 1 – Multi-document Multilingual Summarization Corpus Preparation, Part 1: Arabic, English, Greek, Chinese, Romanian Lei Li, Corina Forascu, Mahmoud El-Haj, George Giannakopoulos

9.35 – 10.05 Session 1 – Multi-document Multilingual Summarization Corpus Preparation, Part 2: Czech, Hebrew and Spanish Michael Elhadad, Sabino Miranda-Jiménez, Josef Steinberger, George Giannakopoulos

Session 2: Multi-document Summarization

10.05 – 10.30 Session 2 – Multi-document Multilingual Summarization and Evaluation Tracks in ACL 2013 MultiLing Workshop George Giannakopoulos


11.00 – 11.30 Session 2 – ACL 2013 MultiLing Pilot Overview Jeff Kubina, John Conroy, Judith Schlesinger

11.30 – 11.50 Session 2 – CIST System Report for ACL MultiLing 2013 – Track 1: Multilingual Multi-document Summarization Lei Li, Wei Heng, Jia Yu, Yu Liu, Shuhong Wan

11.50 – 12.10 Session 2 – Multilingual Multi-Document Summarization with POLY2 Marina Litvak and Natalia Vanetik

12.10 – 12.30 Session 2 – The UWB Summariser at Multiling-2013 Josef Steinberger


14.00 – 15.00 Invited Talk: Natural Language Processing for Analyzing Collective Discourse Dragomir R. Radev, University of Michigan

Workshop 12:

104


15:00 – 15.30 Multilingual Summarization: Dimensionality Reduction and a Step Towards Optimal Term Coverage John Conroy, Sashka T. Davis, Jeff Kubina, Yi-Kai Liu, Dianne P. O'Leary, Judith D Schlesinger


16.00 – 16.20 Session 2 – Using a Keyness Metric for Single and Multi Document Summarisation Mahmoud El-Haj and Paul Rayson

Session 3: Single-document Summarization

16.20 – 16.40 Session 3 – Multilingual Summarization System Based on Analyzing the Discourse Structure at MultiLing 2013 Daniel Anechitei and Eugen Ignat

16.40 – 17.00 Session 3 – Multilingual Single-Document Summarization with MUSE Marina Litvak and Mark Last

17.00 Closing Discussion

105

MULTILING 2013: Multilingual Multi-Document SummarizationthFriday, August 9 , 2013 → Hall 1.4

WORKSHOP PROGRAM:


Session 1: Data Contribution and Exploitation

9.05 – 9.35 Session 1 – Multi-document Multilingual Summarization Corpus Preparation, Part 1: Arabic, English, Greek, Chinese, Romanian Lei Li, Corina Forascu, Mahmoud El-Haj, George Giannakopoulos

9.35 – 10.05 Session 1 – Multi-document Multilingual Summarization Corpus Preparation, Part 2: Czech, Hebrew and Spanish Michael Elhadad, Sabino Miranda-Jiménez, Josef Steinberger, George Giannakopoulos

Session 2: Multi-document Summarization

10.05 – 10.30 Session 2 – Multi-document Multilingual Summarization and Evaluation Tracks in ACL 2013 MultiLing Workshop George Giannakopoulos


11.00 – 11.30 Session 2 – ACL 2013 MultiLing Pilot Overview Jeff Kubina, John Conroy, Judith Schlesinger

11.30 – 11.50 Session 2 – CIST System Report for ACL MultiLing 2013 – Track 1: Multilingual Multi-document Summarization Lei Li, Wei Heng, Jia Yu, Yu Liu, Shuhong Wan

11.50 – 12.10 Session 2 – Multilingual Multi-Document Summarization with POLY2 Marina Litvak and Natalia Vanetik

12.10 – 12.30 Session 2 – The UWB Summariser at Multiling-2013 Josef Steinberger


14.00 – 15.00 Invited Talk: Natural Language Processing for Analyzing Collective Discourse Dragomir R. Radev, University of Michigan

Workshop 12:

104


“Not not bad” is not “bad”: A distributional account of negationKarl Moritz Hermann, Edward Grefenstette and Phil Blunsom

Towards Dynamic Word Sense Discrimination with Random IndexingHans Moen, Erwin Marsi and Björn Gambäck


14.00 – 15.00 Invited Talk: Learning to Ground Meaning in the Visual World Mirella Lapata

15.00 – 15.20 Contributed Talk: A Generative Model of Vector Space Semantics Jacob Andreas and Zoubin Ghahramani

15.20 – 15.40 Contributed Talk: Aggregating Continuous Word Embeddings for Information Retrieval Stephane Clinchant and Florent Perronnin


16.00 – 16.20 Contributed Talk: Answer Extraction by Recursive Parse Tree Descent Christopher Malon and Bing Bai

16.20 – 16.40 Contributed Talk: Recurrent Convolutional Neural Networks for Discourse Compositionality Nal Kalchbrenner and Phil Blunsom

16.40 Panel Discussion

107

CVSC: Workshop on Continuous Vector Space Models and

Their CompositionalitythFriday, August 9 , 2013 → Hall 10

WORKSHOP PROGRAM:

9.00 Opening

9.05 – 10.00 Invited Talk: Structured Prediction with Low-Rank Bilinear Models Xavier Carreras

10.00 – 10.20 Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models Jayant Krishnamurthy and Tom Mitchell

10.20 – 10.40 Learning from Errors: Using Vector-based Compositional Semantics for Parse Reranking Phong Le, Willem Zuidema and Remko Scha


11.00 Poster session

A Structured Distributional Semantic Model : Integrating Structure with SemanticsKartik Goyal, Sujay Kumar Jauhar, Huiying Li, Mrinmaya Sachan, Shashank Srivastava and Eduard Hovy

Letter N-Gram-based Input Encoding for Continuous Space Language ModelsHenning Sperr, Jan Niehues and Alex Waibel

Transducing Sentences to Syntactic Feature Vectors: an Alternative Way to "Parse"?Fabio Massimo Zanzotto and Lorenzo Dell'Arciprete

General estimation and evaluation of compositional distributional semantic modelsGeorgiana Dinu, Nghia The Pham and Marco Baroni

Applicative structure in vector space modelsMarton Makrai, David Mark Nemeskey and Andras Kornai

Determining Compositionality of Expresssions Using Various Word Space Models and MethodsLubomír Krčmář, Karel Jezek and Pavel Pecina

Workshop 13:

106


“Not not bad” is not “bad”: A distributional account of negationKarl Moritz Hermann, Edward Grefenstette and Phil Blunsom

Towards Dynamic Word Sense Discrimination with Random IndexingHans Moen, Erwin Marsi and Björn Gambäck


14.00 – 15.00 Invited Talk: Learning to Ground Meaning in the Visual World Mirella Lapata

15.00 – 15.20 Contributed Talk: A Generative Model of Vector Space Semantics Jacob Andreas and Zoubin Ghahramani

15.20 – 15.40 Contributed Talk: Aggregating Continuous Word Embeddings for Information Retrieval Stephane Clinchant and Florent Perronnin


16.00 – 16.20 Contributed Talk: Answer Extraction by Recursive Parse Tree Descent Christopher Malon and Bing Bai

16.20 – 16.40 Contributed Talk: Recurrent Convolutional Neural Networks for Discourse Compositionality Nal Kalchbrenner and Phil Blunsom

16.40 Panel Discussion

107

CVSC: Workshop on Continuous Vector Space Models and

Their CompositionalitythFriday, August 9 , 2013 → Hall 10

WORKSHOP PROGRAM:

9.00 Opening

9.05 – 10.00 Invited Talk: Structured Prediction with Low-Rank Bilinear Models Xavier Carreras

10.00 – 10.20 Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models Jayant Krishnamurthy and Tom Mitchell

10.20 – 10.40 Learning from Errors: Using Vector-based Compositional Semantics for Parse Reranking Phong Le, Willem Zuidema and Remko Scha


11.00 Poster session

A Structured Distributional Semantic Model : Integrating Structure with SemanticsKartik Goyal, Sujay Kumar Jauhar, Huiying Li, Mrinmaya Sachan, Shashank Srivastava and Eduard Hovy

Letter N-Gram-based Input Encoding for Continuous Space Language ModelsHenning Sperr, Jan Niehues and Alex Waibel

Transducing Sentences to Syntactic Feature Vectors: an Alternative Way to "Parse"?Fabio Massimo Zanzotto and Lorenzo Dell'Arciprete

General estimation and evaluation of compositional distributional semantic modelsGeorgiana Dinu, Nghia The Pham and Marco Baroni

Applicative structure in vector space modelsMarton Makrai, David Mark Nemeskey and Andras Kornai

Determining Compositionality of Expresssions Using Various Word Space Models and MethodsLubomír Krčmář, Karel Jezek and Pavel Pecina

Workshop 13:

106


Teaching NLP and CLthFriday, August 9 , 2013 → Hall 1.5

WORKSHOP PROGRAM:

9.00 Welcome

Olympiads – PAPERS I

9.10 – 9.30 Rosetta Stone Linguistic Problems Bozhidar Bozhanov and Ivan Derzhanski

9.30 – 9.50 Linguistic Problems Based on Text Corpora Boris Iomdin, Alexander Piperski and Anton Somin

9.50 – 10.10 Introducing Computational Concepts in a Linguistic Olympiad Patrick Littell, Lori Levin, Jason Eisner and Dragomir Radev

10.10 – 10.30 Multilingual Editing of Linguistic Problems Ivan Derzhanski

Olympiads – PAPERS II

11.00 – 11.20 Learning from OzCLO, the Australian Computational and Linguistics Olympiad Dominique Estival, John Henderson, Mary Laughren, Diego Mollá, Cathy Bow, Rachel Nordlinger, Verna Rieschild, Andrea C. Schalley, Alexander W. Stanley and Colette Mrowa-Hopkins

11.20 – 11.30 The Swedish Model of Public Outreach of Linguistics to secondary school Students through Olympiads Patrik Roos and Hedvig Skirgård

11.30 – 12.30 Olympiads – PANEL

14.00 – 15.40 Teaching NLP and CL – PAPERS

14.00 – 14.10 Correspondence Seminar: Bringing Linguistics to High Schools Matej Korvas and Vojtech Diatka

14.10 – 14.20 Artificial IntelliDance: Teaching Machine Learning through a Choreography Apoorv Agarwal and Caitlin Trainor

14.20 – 14.30 Treebanking for Data-driven Research in the Classroom John Lee, Ying Cheuk Hui and Yin Hei Kong

Workshop 15:

109

DiscoMT 2013: Discourse in Machine TranslationthFriday, August 9 , 2013 → Hall 4

WORKSHOP PROGRAM:


First Oral Presentation Session

9.10 – 9.30 Meaning Unit Segmentation in English and Chinese: a New Approach to Discourse Phenomena Jennifer Williams, Rafael Banchs and Haizhou Li

9.30 – 9.50 Analysing Lexical Consistency in Translation Liane Guillou

9.50 – 10.10 Implicitation of Discourse Connectives in (Machine) Translation Thomas Meyer and Bonnie Webber

10.10 – 10.30 Associative Texture Is Lost In Translation Beata Beigman Klebanov and Michael Flor


11.00 Poster session, jointly with WMT In addition to posters from the speakers, posters will also be presented for the following papers: Detecting Narrativity to Improve English to French Translation of Simple Past VerbsThomas Meyer, Cristina Grisot and Andrei Popescu-Belis Machine Translation with Many Manually Labeled Discourse ConnectivesThomas Meyer and Lucie Poláková


Second Oral Presentation Session

14.00 – 14.20 Translation of "It" in a Deep Syntax Framework Michal Novak, Anna Nedoluzhko and Zdenek Zabokrtsky

14.20 – 14.40 Feature Weight Optimization for Discourse-Level SMT Sara Stymne, Christian Hardmeier, Jörg Tiedemann and Joakim Nivre

14.40 – 15.30 Closing Discussion15.30 Coffee break, end of the workshop

Workshop 14:

108


Teaching NLP and CLthFriday, August 9 , 2013 → Hall 1.5

WORKSHOP PROGRAM:

9.00 Welcome

Olympiads – PAPERS I

9.10 – 9.30 Rosetta Stone Linguistic Problems Bozhidar Bozhanov and Ivan Derzhanski

9.30 – 9.50 Linguistic Problems Based on Text Corpora Boris Iomdin, Alexander Piperski and Anton Somin

9.50 – 10.10 Introducing Computational Concepts in a Linguistic Olympiad Patrick Littell, Lori Levin, Jason Eisner and Dragomir Radev

10.10 – 10.30 Multilingual Editing of Linguistic Problems Ivan Derzhanski

Olympiads – PAPERS II

11.00 – 11.20 Learning from OzCLO, the Australian Computational and Linguistics Olympiad Dominique Estival, John Henderson, Mary Laughren, Diego Mollá, Cathy Bow, Rachel Nordlinger, Verna Rieschild, Andrea C. Schalley, Alexander W. Stanley and Colette Mrowa-Hopkins

11.20 – 11.30 The Swedish Model of Public Outreach of Linguistics to secondary school Students through Olympiads Patrik Roos and Hedvig Skirgård

11.30 – 12.30 Olympiads – PANEL

14.00 – 15.40 Teaching NLP and CL – PAPERS

14.00 – 14.10 Correspondence Seminar: Bringing Linguistics to High Schools Matej Korvas and Vojtech Diatka

14.10 – 14.20 Artificial IntelliDance: Teaching Machine Learning through a Choreography Apoorv Agarwal and Caitlin Trainor

14.20 – 14.30 Treebanking for Data-driven Research in the Classroom John Lee, Ying Cheuk Hui and Yin Hei Kong

Workshop 15:

109

DiscoMT 2013: Discourse in Machine TranslationthFriday, August 9 , 2013 → Hall 4

WORKSHOP PROGRAM:


First Oral Presentation Session

9.10 – 9.30 Meaning Unit Segmentation in English and Chinese: a New Approach to Discourse Phenomena Jennifer Williams, Rafael Banchs and Haizhou Li

9.30 – 9.50 Analysing Lexical Consistency in Translation Liane Guillou

9.50 – 10.10 Implicitation of Discourse Connectives in (Machine) Translation Thomas Meyer and Bonnie Webber

10.10 – 10.30 Associative Texture Is Lost In Translation Beata Beigman Klebanov and Michael Flor


11.00 Poster session, jointly with WMT In addition to posters from the speakers, posters will also be presented for the following papers: Detecting Narrativity to Improve English to French Translation of Simple Past VerbsThomas Meyer, Cristina Grisot and Andrei Popescu-Belis Machine Translation with Many Manually Labeled Discourse ConnectivesThomas Meyer and Lucie Poláková


Second Oral Presentation Session

14.00 – 14.20 Translation of "It" in a Deep Syntax Framework Michal Novak, Anna Nedoluzhko and Zdenek Zabokrtsky

14.20 – 14.40 Feature Weight Optimization for Discourse-Level SMT Sara Stymne, Christian Hardmeier, Jörg Tiedemann and Joakim Nivre

14.40 – 15.30 Closing Discussion15.30 Coffee break, end of the workshop

Workshop 14:

108


14.30 – 14.40 Learning Computational Linguistics through NLP Evaluation Events: the experience of Russian evaluation initiative Anastasia Bonch-Osmolovskaya, Svetlana Toldova and Olga Lyashevskaya

14.40 – 15.00 A Virtual Manipulative for Learning Log-Linear Models Francis Ferraro and Jason Eisner

15.00 – 15.20 Teaching the Basics of NLP and ML in an Introductory Course to Information Science Apoorv Agarwal

15.20 – 15.40 Semantic Technologies in IBM Watson Alfio Gliozzo, Or Biran, Siddharth Patwardhan and Kathleen McKeown

16.00 – 17.30 Teaching NLP and CL – PANEL

14.30 – 14.40 Learning Computational Linguistics through NLP Evaluation Events: the experience of Russian evaluation initiative Anastasia Bonch-Osmolovskaya, Svetlana Toldova and Olga Lyashevskaya

14.40 – 15.00 A Virtual Manipulative for Learning Log-Linear Models Francis Ferraro and Jason Eisner

15.00 – 15.20 Teaching the Basics of NLP and ML in an Introductory Course to Information Science Apoorv Agarwal

15.20 – 15.40 Semantic Technologies in IBM Watson Alfio Gliozzo, Or Biran, Siddharth Patwardhan and Kathleen McKeown

16.00 – 17.30 Teaching NLP and CL – PANEL

Notes


Notes






This book is also available as PDF at:a�2013.org/site/conference-handbook.pdf