Embed Size (px)
Citation preview
Workshops
Bibliometric-Enhanced Information Retrieval:7th International BIR Workshop
Philipp Mayr1(B), Ingo Frommholz2, and Guillaume Cabanac3
1 GESIS – Leibniz-Institute for the Social Sciences, Cologne, [email protected]
2 Institute for Research in Applicable Computing,University of Bedfordshire, Luton, UK
[email protected] Computer Science Department, University of Toulouse, IRIT UMR 5505,
Toulouse, [email protected]
The Bibliometric-enhanced Information Retrieval (BIR) workshop series hasstarted at ECIR in 2014 [1] and serves as the annual gathering of IR researcherswho address various information-related tasks on scientific corpora and biblio-metrics [2]. The workshop features original approaches to search, browse, anddiscover value-added knowledge from scientific documents and related informa-tion networks (e.g., terms, authors, institutions, references). We welcome con-tributions elaborating on dedicated IR systems, as well as studies revealingoriginal characteristics on how scientific knowledge is created, communicated,and used. The first BIR workshops set the research agenda by introducingthe workshop topics, illustrating state-of-the-art methods, reporting on currentresearch problems, and brainstorming about common interests. For the fourthworkshop, co-located with the ACM/IEEE-CS JCDL 2016, we broadened theworkshop scope and interlinked the BIR workshop with the natural languageprocessing (NLP) and computational linguistics field [3]. This 7th full-day BIRworkshop at ECIR 20181 aims to foster a common ground for the incorpora-tion of bibliometric-enhanced services (including text mining functionality) intoscholarly search engine interfaces. In particular we address specific communi-ties, as well as studies on large, cross-domain collections. This workshop strivesto feature contributions from core bibliometricians and core IR specialists whoalready operate at the interface between scientometrics and IR. Workshop pro-ceedings will be published in open access with the CEUR workshop proceedingspublication service.
References
1. Mayr, P., Scharnhorst, A., Larsen, B., Schaer, P., Mutschke, P.: Bibliometric-enhanced information retrieval. In: de Rijke, M., Kenter, T., de Vries, A.P.,Zhai, C.X., de Jong, F., Radinsky, K., Hofmann, K. (eds.) ECIR 2014. LNCS,vol. 8416, pp. 798–801. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06028-6 99
1 http://bit.ly/bir2018.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, pp. 827–828, 2018.https://doi.org/10.1007/978-3-319-76941-7
828 P. Mayr et al.
2. Mayr, P., Scharnhorst, A.: Scientometrics and information retrieval: weak-links revi-talized. Scientometrics 102(3), 2193–2199 (2015)
3. Cabanac, G., Chandrasekaran, M.K., Frommholz, I., Jaidka, K., Kan, M.Y.,Mayr, P., Wolfram, D.: Report on the joint workshop on bibliometric-enhancedinformation retrieval and natural language processing for digital libraries (BIRNDL2016). SIGIR Forum 50(2), 36–43 (2016)
BroDyn’18: Workshop on Analysis of BroadDynamic Topics over Social Media
Tamer Elsayed1(B), Walid Magdy2, Mucahid Kutlu1, Maram Hasanain1,and Reem Suwaileh1
1 Qatar University, Doha, Qatar{telsayed,mucahidkutlu,maram.hasanain,reem.suwaileh}@qu.edu.qa
2 University of Edinburgh, Edinburgh, [email protected]
In recent years, users developed a widespread perception of social media as newssources that they follow (almost all day long) to get updated on topics of interest.Many of those topics attract long-standing user interest (i.e., stay active for longperiods of time), are very broad (i.e., cover many subtopics), and are dynamic(i.e., develop and change focus over time with subtopics becoming obsolete andnew subtopics emerging). Such kind of broad and dynamic topics can run for fewweeks, such as crisis events (e.g., “Hurricane Irma”), or up to years, such as “theSyrian conflict”. Other examples of such topics include “Refugees in Europe”,“Qatar Crisis”, “Brexit” to name a few.
Effective exploitation of content posted on social media that is relevant tobroad dynamic topics requires adaptive techniques to effectively capture thechanging aspects of topics. The techniques should also be scalable and real-timeto cope with the large, rapidly flowing stream, and reliable to perform effectivelyover the long duration of the topic. Moreover, new evaluation frameworks forsuch domain are also needed with novel evaluation measures that capture thenature of topics (and thus systems) and new large reusable datasets that enablerunning meaningful and representative experiments.
BroDyn workshop1 aims at building a community interested in developingand exchanging ideas and methods for analyzing social media for broad dynamictopics. It also aims at understanding the limitations of existing techniques inanswering emerging information needs for such topics, and proposing new tech-niques, evaluation methods, and test collections to address these limitations. Itis designed to bring together audience at all levels, including researchers fromacademia and industry as well as potential users (e.g., journalists and socialscientists), to create a forum for discussing recent advances in this area.
The half-day workshop (held in conjunction with ECIR’18) covers severaltopics of interest including (but not limited to) adaptive filtering/topic track-ing, adaptive summarization, multilingual topic/event detection, online/dynamictopic modeling, retrospective generation of timelines, cross-media filtering, real-time/scalable techniques of processing high-volume streams, and evaluation
1 https://sites.google.com/view/brodyn2018.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, pp. 829–830, 2018.https://doi.org/10.1007/978-3-319-76941-7
830 T. Elsayed et al.
techniques and novel test collections. To encourage research on such tasks, wereleased two datasets: (1) GE2017, a dataset of around 18M tweets on the BritishGeneral Elections 2017, and (2) USPresElect2016, a dataset of 3,450 labelledtweets on the US Presidential Elections 2016.
Second International Workshop on RecentTrends in News Information Retrieval
(NewsIR’18)
Miguel Martinez1, Dyaa Albakour1(B), David Corney5, Julio Gonzalo2,Barbara Poblete3, and Andreas Vlachos4
1 Signal Media, London, UK{miguel.martinez,dyaa.albakour}@signal.uk.com
2 UNED, Madrid, [email protected]
3 University of Chile, Santiago, [email protected]
4 University of Sheffield, Sheffield, [email protected]
5 Factmata, London, [email protected]
https://www.signal.uk.com
Abstract. The news industry has undergone a revolution in the pastdecade, with substantial changes continuing to this day. News consump-tion habits are changing due to the increase in both the volume of newsand the variety of sources. Readers need new mechanisms to cope withthis vast volume of information in order to not only find a signal inthe noise, but also to understand what is happening in the world giventhe multiple points of view describing every event. These challenges injournalism relate to IR and NLP fields such as: verification of a source’sreliability; the integration of news with other sources of information; real-time processing of both news content and social streams; de-duplicationof stories; and entity detection and disambiguation. Although IR andNLP have been applied to news for decades, the changing nature ofthe space requires fresh approaches and a closer collaboration with ourcolleagues from the journalism environment. The goal of this workshopis to stimulate such discussion between the communities and to shareinteresting approaches to solve real user problems.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, p. 831, 2018.https://doi.org/10.1007/978-3-319-76941-7
Workshop on Social Aspects in Personalizationand Search (SoAPS 2018)
Ludovico Boratto1(B) and Giovanni Stilo2
1 Digital Humanities, Eurecat Camı Antic de Valencia 54, 08005 Barcelona, [email protected]
2 Dipartimento di Informatica, Sapienza Universita di Roma,Via Salaria 113, 00198 Rome, Italy
In order to improve the web experience of the users, classic personalization tech-nologies (e.g., recommender systems) and search engines usually rely on staticschemes. Indeed, users are allowed to express ratings in a fixed range of valuesfor a given catalogue of products, or to express a query that usually returns thesame set of webpages/products for all the users.
With the advent of communication systems (social media platforms, instantmessaging systems, speech recognition and transcription tools, etc.), users havebeen allowed to create new content and to express opinions and preferences innew forms (e.g., likes, textual comments, and audio feedbacks). Moreover, thesocial interactions can provide information on who influences whom. Being ableto mine usage and collaboration patterns that arise thanks to social aspectsand to analyze the collective cooperations, opens new frontiers in the generationof personalization services and in the improvement of search engines. Moreover,recent technological advances, such as deep learning, are able to provide a contextto the analyzed data (e.g., word embeddings provide a vector representation ofthe words in a corpus, considering the context in which a word has been used).
Our workshop solicited contributions in all topics related to employing socialaspects for personalization and search purposes, focused (but not limited) to thefollowing list:
– Recommender systems– Search and tagging– Query expansion– User modeling and profiling– Advertising and ad targeting– Content classification, categorization, and clustering– Using social network features/community detection algorithms for personal-ization and search purposes
– Employing speech transcription in personalization and search– Building benchmarking datasets– Novel evaluation methodologies in the social context
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, p. 832, 2018.https://doi.org/10.1007/978-3-319-76941-7
First International Workshop on NarrativeExtraction from Texts: Text2Story 2018
Alípio Mário Jorge1,2(B) , Ricardo Campos1,3 , Adam Jatowt4 ,and Sérgio Nunes1,2
1 INESC TEC, Porto, [email protected]
2 University of Porto, Porto, Portugal3 Polytechnic Institute of Tomar, Tomar, Portugal
4 Kyoto University, Kyoto, Japan
Keywords: Information extraction · Narrative extraction
1 Synopsis
The increasing availability of text information in the form of news articles, com-ments or posts poses new challenges for those who aim to understand the sto-ryline of an event. Although understanding natural language text has improvedover the last couple of years with several research works emerging on the groundsof information extraction and text mining, the problem of constructing consis-tent narrative structures is yet to be solved. We have a challenging path aheadof us for the development and improvement of algorithms that automaticallyidentify, interpret and relate the different elements of a narrative which will belikely spread among different sources. In this first workshop on this topic, heldat the 40th European Conference on Information Retrieval (ECIR 2018), weaim to foster the discussion of recent advances in the link between InformationRetrieval (IR) and formal narrative representations from texts. More specifi-cally, we aim to capture a wide range of multidisciplinary issues related to thetext-to-narrative-structure and to its various related tasks. These include eventidentification; narrative representation language; sentiment and opinion detec-tion; argumentation mining; narrative summarization; storyline visualization;temporal aspects of storylines; story evolution and shift detection; causal rela-tion extraction and arrangement; evaluation methodologies for narrative extrac-tion; big data applied to narrative extraction; resources and dataset showcase;personalization and recommendation; user profiling and user behavior modeling;credibility; fact checking and bots influence. This workshop features a diversityof tasks and techniques with promising results for an exciting event.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, pp. 833–834, 2018.https://doi.org/10.1007/978-3-319-76941-7
834 A. M. Jorge et al.
Acknowledgments. This work is financed by the ERDF – European Regional Devel-opment Fund through the Operational Programme for Competitiveness and Interna-tionalisation - COMPETE 2020 Programme within project «POCI-01-0145-FEDER-006961», and by National Funds through the FCT – Fundação para a Ciência e aTecnologia (Portuguese Foundation for Science and Technology) as part of projectUID/EEA/50014/2013.
Tutorials
Neural Networks for Information Retrieval
Tom Kenter1(B), Alexey Borisov2, Christophe Van Gysel3, Mostafa Dehghani3,Maarten de Rijke3, and Bhaskar Mitra4
1 Booking.com, Amsterdam, [email protected]
2 Yandex, Moscow, [email protected]
3 University of Amsterdam, Amsterdam, Netherlands{cvangysel,dehghani,derijke}@uva.nl
4 Microsoft, University College London, London, [email protected]
Abstract. Machine learning plays a role in many aspects of modernIR systems, and deep learning is applied in all of them. The fast paceof modern-day research has given rise to many approaches to many IRproblems. The amount of information available can be overwhelmingboth for junior students and for experienced researchers looking for newresearch topics and directions. The aim of this full-day tutorial is to givea clear overview of current tried-and-trusted neural methods in IR andhow they benefit IR.
Prompted by the advances of deep learning in computer vision, neuralnetworks (NNs) have resurfaced as a popular machine learning paradigmin many other directions of research, including IR. Recent years have seenNNs being applied to all key parts of the typical modern IR pipeline,such as click models, core ranking algorithms, dialogue systems, entityretrieval, knowledge graphs, language modeling, question answering, andtext similarity. A key advantage that sets NNs apart from many learningstrategies employed earlier, is their ability to work from raw input data.Where designing features used to be a crucial aspect and contribution ofnewly proposed IR approaches, the focus has shifted to designing networkarchitectures instead. As a consequence, many different architectures andparadigms have been proposed, such as auto-encoders, recursive net-works, recurrent networks, convolutional networks, various embeddingmethods, and deep reinforcement learning. The aim of this tutorial is toprovide an overview of the main network architectures currently appliedin IR and to show how they relate to previous work. The tutorial coversmethods applied in industry and academia, with in-depth insights intothe underlying theory, core IR tasks, applicability, key assets and hand-icaps, efficiency and scalability concerns, and tips & tricks. We expectthe tutorial to be useful both for academic and industrial researchers andpractitioners who either want to develop new neural models, use themin their own research in other areas or apply the models described hereto improve actual IR systems.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, p. 837, 2018.https://doi.org/10.1007/978-3-319-76941-7
Tutorial on Semantic Search on Text
Lynda Tamine1(B) and Lorraine Goeuriot2
1 University of Toulouse UPS, IRIT, 118 route de Narbonne,31062 Toulouse Cedex 9, France
[email protected] University of Grenoble Alpes, CNRS, Grenoble INP, LIG,
621 avenue Centrale, 38400 Saint-Martin-d’Heres, 38000 Grenoble, [email protected]
1 Tutorial Abstract
This tutorial will first explore the peculiarities of medical and health-relatedqueries with respect to various facets (eg. vocabulary, users expertise, task) withthe attempt of better understanding the underlying human intent. Second, asenvisioned in semantic search, we will focus on the techniques and theoreticalmodels that go beyond lexical matching to drive the search. We will cover boththe symbolic semantics through the use of external resources (eg. UMLS, MeSH,Gene Ontology) and the distributional semantics relying on words collocations inthe corpus including recent representation learning approaches of concepts anddocuments. Third, we will develop a roadmap on the main evaluation frameworksused in medical IR and then particularly examine and compare the effectivenessof semantic-based IR approaches. Finally, we summarize the research findings inthe area and outline the key open research questions. To sum up, the goals ofthe tutorial are the following:
– Summarize the lessons that can be drawn from studies investigating the pecu-liarities of medical-related information needs;
– Present state-of-the art semantic search models supporting medical IRprocesses;
– Describe the major medical search evaluation benchmarks used in the IRcommunity and report the key result trends achieved by the application ofsemantic IR models.
2 Organizers
Lynda Tamine is a Professor of Computer Science at the Paul Sabatier uni-versity in Toulouse and member of the Institut de Recherche en Informatiquede Toulouse (IRIT). Her research interests include modelling and evaluationof medical, contextual, collaborative and social information retrieval. LorraineGoeuriot is an associate professor in Universit Grenoble Alpes. Her researchinterests include medical information retrieval and the evaluation of informationretrieval.c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, p. 838, 2018.https://doi.org/10.1007/978-3-319-76941-7
Extreme Multi-label Classificationfor Information Retrieval
Krzysztof Dembczynski1 and Rohit Babbar2(B)
1 Poznan University of Technology, Poznan, Poland2 Aalto University, Helsinki, Finland
The goal in extreme multi-label classification is to learn a classifier which canassign a small subset of relevant labels to an instance from an extremely largeset of target labels. It has been shown that this framework can be applied toeffectively address the challenges in ranking, recommendation and automatictagging systems. Extreme classification simultaneously exhibits two seeminglycontrary challenges – data abundance as a whole for all the labels on one hand,and data scarcity for individual labels on the other hand. The former poses acomputational challenge while the latter posses a statistical challenge.
In the tutorial we will motivate extreme classification as an active and rapidlygrowing research area with many potential applications in information retrieval.We will present three main strands for addressing the challenges which consist of(i) label embedding methods [2, 8], (ii) tree-based methods [3, 6], and (iii) smartone-vs-rest approaches [1, 7]. Futhermore, we will discuss extreme classifica-tion solutions in the domain of deep networks [4, 5]. Finally, we will highlightopen benchmark datasets derived from sources such as Wikipedia, Amazon andDelicious,1 and also live demonstrate open source code by running it on thesebenchmark datasets.
References
1. Babbar, R., Scholkopf, B.: DiSMEC: distributed sparse machines for extreme multi-label classification. In: WSDM 2017, pp. 721–729. ACM (2017)
2. Bhatia, K., Jain, H., Kar, P., Varma, M., Jain, P.: Sparse local embeddings forextreme multi-label classification. In: NIPS 2015, pp. 730–738. Curran AssociatesInc. (2015)
3. Jasinska, K., Dembczynski, K., Busa-Fekete, R., Pfannschmidt, K., Klerx, T.,Hullermeier, E.: Extreme F-measure maximization using sparse probability esti-mates. In: ICML 2016, vol. 48, pp. 1435–1444. PMLR (2016)
4. Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient textclassification. CoRR abs/1607.01759 (2016)
5. Liu, J., Chang, W.C., Wu, Y., Yang, Y.: Deep learning for extreme multi-label textclassification. In: SIGIR 2017, pp. 115–124. ACM (2017)
6. Prabhu, Y., Varma, M.: FastXML: a fast, accurate and stable tree-classifier forextreme multi-label learning. In: KDD 2014, pp. 263–272. ACM (2014)
1 http://manikvarma.org/downloads/XC/XMLRepository.html.
c© Springer International Publishing AG, part of Springer Nature 2018G. Pasi et al. (Eds.): ECIR 2018, LNCS 10772, pp. 839–840, 2018.https://doi.org/10.1007/978-3-319-76941-7
840 K. Dembczynski and R. Babbar
7. Yen, I.E., Huang, X., Dai, W., Ravikumar, P., Dhillon, I., Xing, E.: PPDSparse:a parallel primal-dual sparse method for extreme classification. In: KDD 2017,pp. 545–553. ACM (2017)
8. Yu, H.F., Jain, P., Kar, P., Dhillon, I.: Large-scale multi-label learning with missinglabels. In: ICML 2014, vol. 32, pp. 593–601. PMLR (2014)
Author Index
Abdulahhad, Karam 563Agosti, Maristella 385Agrawal, Shriyansh 811Agrawal, Sweta 141Ai, Qingyao 537Albakour, Dyaa 780, 831Al-Obeidat, Feras 737Amini, Massih-Reza 398Asghar, Nabiha 154Awekar, Amit 141Azzopardi, Leif 210
Babbar, Rohit 839Badjatiya, Pinkesh 180Bagheri, Ebrahim 665, 737Bahrainian, Seyed Ali 16Balasubramanian, Niranjan 750Balikas, Georgios 398Balog, Krisztian 625, 644Bashari, Masoud 737Bellogín, Alejandro 357Berberich, Klaus 657Bevendorff, Janek 820Bhatia, Pankaj 604Boratto, Ludovico 371, 832Borisov, Alexey 837Brazier, David 237Bucco, Riccardo 385Busato, Giulio 385
Cabanac, Guillaume 827Callan, Jamie 577Campos, Ricardo 684, 715, 806, 833Carta, Salvatore 371Charbonnier, Jean 797Cheng, Xueqi 289, 303Claveau, Vincent 251Cohen, Daniel 127Corney, David 780, 831Crestani, Fabio 16, 801Croft, W. Bruce 127, 537Culpepper, J. Shane 544
Dai, Zhuyun 577Dehghani, Mostafa 837de Rijke, Maarten 837Dembczyński, Krzysztof 839Dey, Kuntal 29, 529Di Nunzio, Giorgio Maria 672Ding, Heng 625Dür, Alexander 102
Eickhoff, Carsten 167, 523Elsayed, Tamer 829Esquivel, José 780
Fairon, Cédrick 618Fang, Anjie 263, 765Fani, Hossein 737Färber, Michael 598, 815Farhoodi, Mojgan 715Fenu, Gianni 371Ferrante, Marco 197Ferro, Nicola 197Filzmoser, Peter 102Fornari, Giacomo 385Frommholz, Ingo 827
Galkó, Ferenc 523Ganea, Octavian-Eugen 167, 611Gangwar, Abhishek 604Garg, Kritika 29Garg, Shweta 591Garigliotti, Darío 625, 644Gertz, Michael 3Gharebagh, Sajad Sotudeh 411Goel, Shivali 591Goeuriot, Lorraine 838Gonzalo, Julio 831Goyal, Pawan 604Graner, Lukas 454Granitzer, Michael 638Grnarova, Paulina 611Guo, Jiafeng 289, 303Gupta, Kartik 333
Gupta, Manish 45, 59, 180, 556Gupta, Shashank 59, 556
Hagen, Matthias 820Haghir Chehreghani, Morteza 466Haghir Chehreghani, Mostafa 466Halvani, Oren 454Harvey, Morgan 237Hasanain, Maram 829Hasibi, Faegheh 707Haug, Till 611Herrera, Jose 507Hoey, Jesse 154Hou, Yuexian 424
Jalan, Raksha 45Jansen, Peter 750Jatowt, Adam 598, 684, 729, 806, 815, 833Jia, Haofeng 758Jiang, Xin 154Jimmy 72Jorge, Alípio Mário 684, 806, 833Jun, Lang 89
Kando, Noriko 223Kaushik, Saroj 29, 529Kenter, Tom 837Kingrani, Suneel Kumar 550Klakow, Dietrich 657Koopman, Bevan 72Krestel, Ralf 114Kurisinkel, Litton J. 180Kutlu, Mucahid 829Kwon, Heeyoung 750
Laclau, Charlotte 398Lam, Wai 773Lan, Man 89Lan, Yanyan 289, 303Langeli, Andrea 385Levene, Mark 550Li, Sheng 89Li, Wei 276Li, Xiang 316Lin, Xinshi 773Liu, Yiqun 223
Losada, David E. 801Luo, Cheng 223
Ma, Shaoping 223Macdonald, Craig 263, 439, 544, 699, 765Mackenzie, Joel 544Madhok, Rishi 591Magalhães, João 570Magdy, Walid 829Maji, Subhadeep 604Majumder, Anirban 604Majumder, Prasenjit 787Mangaravite, Vítor 684, 806Mansouri, Behrooz 715Mao, Jiaxin 223Martinez, Miguel 780, 831Martínez-Castaño, Rodrigo 801Mathur, Neeraj 811Maxwell, David 210Mayr, Philipp 827McCreadie, Richard 263, 765McDonald, Graham 439, 699Mehta, Parth 787Mehta, Sameep 744Meladianos, Polykarpos 481Mele, Ida 16Mishra, Arunav 657Mitra, Bhaskar 837Mitrović, Sandra 345Mou, Lili 154Mourão, André 570
Neshati, Mahmood 411Nicula, Bogdan 678Nikolentzos, Giannis 481Nørvåg, Kjetil 494Nunes, Célia 684, 806Nunes, Sérgio 833
O’Connor, Brendan 537Oualil, Youssef 657Ounis, Iadh 263, 439, 699, 765Ozdikis, Ozer 494
Palshikar, Girish Keshav 59, 556Pande, Abhay 604
842 Author Index
Parra, Denis 507Pasquali, Arian 684, 806Patra, Bidyut Kr. 632Pawar, Sachin 59, 556Pichel, Juan C. 801Piras, Luca 371Poblete, Barbara 507, 831Pollak, Senja 692Pontarollo, Silvia 197Potthast, Martin 820Poupart, Pascal 154Pudi, Vikram 333Purpura, Alberto 385
Qiu, Long 89
Rahgozar, Maseud 715Ramalho, Rúben 570Ramampiaro, Heri 494Ramrakhiyani, Nitin 59, 556Rauber, Andreas 102Rebedea, Traian 678Reddy, Y. Raghu 811Redko, Ievgen 398Renders, Jean-Michel 722Repke, Tim 114Rocco, Giacomo 385Rohden, Birte 797Rostami, Peyman 411Rothman, John 797Roussinov, Dmitri 651Ruseti, Stefan 678
Sachdeva, Noveen 333Samanta, Suranjana 744Sanagavarapu, Lalit Mohan 811Sánchez, Pablo 357Saule, Erik 758Scholer, Falk 544Seifert, Christin 638Shahshahani, Mahsa S. 707Shakery, Azadeh 707Shrivastava, Ritvik 29, 529Si, Luo 89Silvello, Gianmaria 385Singh, Gaurav 345Singh, Mittul 657Sohmen, Lucia 797Song, Dawei 316, 424Specht, Günther 584
Spitz, Andreas 3Sreepada, Rama Syamala 632Stein, Benno 820Štihec, Jan 692Stilo, Giovanni 832Su, Ting 765Suarez, Axel 780Sumikawa, Yasunobu 729Sun, Shuyuan 276Surdeanu, Mihai 750Suwaileh, Reem 829
Tamine, Lynda 838Tezza, Alessandro 385Thiemann, Alexander 598, 815Tian, Junfeng 89Trikha, Anil Kumar 665Trivedi, Harsh 750Tschuggnall, Michael 584
Van Gysel, Christophe 837Varma, Vasudeva 45, 59, 180, 556Vazirgiannis, Michalis 481Vlachos, Andreas 831Vogel, Inna 454Vogels, Thijs 167Vonteru, Kondalarao 604
Wang, Jingang 89Wang, Panpan 424Wang, Qi 276Wang, Tianshu 424Wartena, Christian 797Wilkens, Rodrigo 618Witt, Nils 638Wu, Yuanbin 89Wurzinger, Stefan 584
Xu, Jun 289, 303Xu, Wukui 276Xypolopoulos, Christos 481
Yang, Xiao 263
Zahedi, Mohammad Sadegh 715Zamani, Hamed 707Zangerle, Eva 584Zarrinkalam, Fattane 665, 737Zhang, Dell 550Zhang, Maoyuan 276
Author Index 843
Zhang, Min 223Zhang, Peng 316Zhang, Ruqing 289, 303Zhang, Shuo 625
Zhang, Yazhou 316Zilio, Leonardo 618Žnidaršič, Martin 692Zuccon, Guido 72
844 Author Index
