Chart-based RRG parsing using an automatically extracted RRG …€¦ · CO NUC V think RP Asterix...

Design of RRG Grammars Automatic RRG Grammar Extraction Parsing experiments Issues Summary & Outlook

Chart-based RRG parsingusing an automatically extracted

RRG grammar with features

David Arps & Tatiana Bladier & Laura Kallmeyer

International Conference on Role and Reference Grammar19 August 2019

University at Buffalo, The State University of New York

1 / 32

Overview

Design of RRG Grammars

Automatic RRG Grammar Extraction

Parsing experiments

Issues

Summary & Outlook

2 / 32

Introduction

1 RRG annotated treebank:RRGBank [2],

2 extract RRG elementarytrees automatically,

3 use these elementarytrees for RRG parsing.

SENTENCE

CLAUSE

DEF-OP

holiday

3 / 32

Introduction

SENTENCE

CLAUSE

NP↓ NUC

DEF-OP

holiday

3 / 32

Introduction

SENTENCE

CLAUSE

NP↓ NUC

DEF-OP

holiday

3 / 32

Outline

Parsing experiments

Issues

Summary & Outlook

4 / 32

RRGbank

? Corpus of RRG annotated sentences [2]→ automatically converted from PennTreebank,→ manually checked and validated;

? 395 gold sentences, 1090 silverannotated sentences;

? RRGbank and RRG annotation tool:rrgbank.phil.hhu.de.

SENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP

CLAUSETNS

5 / 32

Removing crossing branchesSENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP

CLAUSETNS

SENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP [OP=CL]

CLAUSETNS? we transform the RRG structures to remove crossing branches,

? we mark the original position of the node with [op=cl],? original tree structure is easily recovered.

6 / 32

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP

CLAUSETNS

SENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP [OP=CL]

CLAUSETNS? we transform the RRG structures to remove crossing branches,? we mark the original position of the node with [op=cl],

? original tree structure is easily recovered.

6 / 32

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP

CLAUSETNS

SENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP [OP=CL]

CLAUSETNS? we transform the RRG structures to remove crossing branches,? we mark the original position of the node with [op=cl],? original tree structure is easily recovered.

6 / 32

Operator projection and periphery can be recovered

SENTENCE

CLAUSE

Japanese

AP-PERI

buyers

TNS-OP

CLAUSETNS

SENTENCE

CLAUSE

Japanese

CORECLM

PERIPHERY

buyerswere

CLAUSETNS

7 / 32

Elementary trees in RRG Grammars

? We follow Kallmeyer et al. (2013) and Osswald & Kallmeyer(2018) [3, 4] in design of the elementary trees in our grammar.

? Three tree composition operations:→ substitution ( argument slot filling)→ wrapping substitution (displaced argument slot filling)→ sister adjunction ( adding operators and periphery elements);

? Such RRG grammars capture long-distance dependencies→ for example, WH-movement.

8 / 32

? Three tree composition operations:

→ substitution ( argument slot filling)→ wrapping substitution (displaced argument slot filling)→ sister adjunction ( adding operators and periphery elements);

8 / 32

? Three tree composition operations:→ substitution ( argument slot filling)

→ wrapping substitution (displaced argument slot filling)→ sister adjunction ( adding operators and periphery elements);

8 / 32

? Three tree composition operations:→ substitution ( argument slot filling)→ wrapping substitution (displaced argument slot filling)

→ sister adjunction ( adding operators and periphery elements);

8 / 32

? Three tree composition operations:→ substitution ( argument slot filling)→ wrapping substitution (displaced argument slot filling)→ sister adjunction ( adding operators and periphery elements);

8 / 32

Combination operations: Substitution and sister adjunction

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

Sentence: I have felt many aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

NP↓ CORE*N

AP-PERI

aftershocks

9 / 32

CORE∗

TNS-OP [OP=CL]

SENTENCE

CLAUSE

NP↓ NUC

NP↓ CORE*N

AP-PERI

aftershocks

9 / 32

SENTENCE

CLAUSE

I felt

AP-PERI

aftershocks

TNS-OP [OP=CL]

10 / 32

Combination operations: Wrapping substitution

CL↓CO

Asterix

Obelix

Asterix

Sentence: What does Asterix think Obelix drank

11 / 32

CL↓CO

Asterix

Obelix

Asterix

11 / 32

CL↓CO

Asterix

Obelix

Asterix

11 / 32

CL↓CO

Asterix

Obelix

Asterix

11 / 32

Elementary trees with features

RRGbank Extracted Elementary Trees

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

] [NUC-O rOPS [NP -]

? elementary trees are enhanced with features

→ edge features→ node features

12 / 32

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

? elementary trees are enhanced with features→ edge features

→ node features

12 / 32

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

? elementary trees are enhanced with features→ edge features→ node features

12 / 32

Edge featuresRRGbank Extracted Elementary Trees

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

Left and right edge feature structures:

? unify adjacent structures in the derived tree? model ordering constraints? percolate upwards until phrasal nodes

13 / 32

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

Left and right edge feature structures:? unify adjacent structures in the derived tree

? model ordering constraints? percolate upwards until phrasal nodes

13 / 32

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

Left and right edge feature structures:? unify adjacent structures in the derived tree? model ordering constraints

? percolate upwards until phrasal nodes

13 / 32

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

Left and right edge feature structures:? unify adjacent structures in the derived tree? model ordering constraints? percolate upwards until phrasal nodes

13 / 32

Node featuresRRGbank Extracted Elementary Trees

DEF-OP

CORE-N

average placeholder

DEF-OP

CORE-N

average

[DEF -OPS [NP -]

][DEF +OPS [NP +]

][DEF +]

[OP=NP]

[NUC-O lOPS [NP -]

? One feature structure per node:• unify during tree composition• store syntactic or syn-sem interface information.

? Unification successful → accept parse tree

14 / 32

Outline

Parsing experiments

Issues

Summary & Outlook

15 / 32

RRG Grammar extraction algorithm (1)

? Elementary tree extraction inspired by Xia [6] algorithmfor induction of Tree-Adjoining Grammars.

? Top-down extraction of elementary trees.? Heuristics from head-modifier percolation tables.? We use RRG structures from RRGbank for automatic grammarinduction→ rrgbank.phil.hhu.de.

16 / 32

RRG Grammar extraction algorithm (2)

CLAUSE

DEF-OP

average

dropped

NUC NP

points

TNS-OP [OP=CL]

DEF-OP[OP = NP,DEF = +]

average

CORE∗

TNS-OP[OP = CL,TNS = past]

CLAUSE

NP↓ NUC

dropped

COREN∗

points

17 / 32

Outline

Parsing experiments

Issues

Summary & Outlook

18 / 32

Chart-based RRG Parser TuLiPA

? input: set of elementary trees and sentences to parse;

? output: all derivations that can be derived by combining theelementary trees;

? standard CYK algorithm;? bottom-up, left-to-right traversion of the derived tree;? software: TuLiPA RRG parser [1]

(https://github.com/spetitjean/TuLiPA-frames)TuLiPA = Tübingen Linguistic Parsing Architecture;

? suitable for hand-crafted precision RRG grammars;? suitable for automatically extracted RRG grammars.

19 / 32

? input: set of elementary trees and sentences to parse;? output: all derivations that can be derived by combining theelementary trees;

? standard CYK algorithm;? bottom-up, left-to-right traversion of the derived tree;? software: TuLiPA RRG parser [1]

19 / 32

? standard CYK algorithm;

? bottom-up, left-to-right traversion of the derived tree;? software: TuLiPA RRG parser [1]

19 / 32

? standard CYK algorithm;? bottom-up, left-to-right traversion of the derived tree;

? software: TuLiPA RRG parser [1](https://github.com/spetitjean/TuLiPA-frames)TuLiPA = Tübingen Linguistic Parsing Architecture;

19 / 32

? standard CYK algorithm;? bottom-up, left-to-right traversion of the derived tree;? software: TuLiPA RRG parser [1](https://github.com/spetitjean/TuLiPA-frames)TuLiPA = Tübingen Linguistic Parsing Architecture;

19 / 32

? suitable for hand-crafted precision RRG grammars;

? suitable for automatically extracted RRG grammars.

19 / 32

Extracted RRG grammar

• removed punctuation• exhaustive parsing (i.e. not probabilistic, overgenerating a lot)

• 2 versions:1 no features2 edge features for operators model adjunction constraints

• do feature structures eliminate parse trees that contradictlinguistic intuitions?

20 / 32

Parsing experiments

Gold Grammar Silver Grammarw feats w/o feats w feats w/o feats

Sentences 395 1480avg. sentence length 6.1 8.0token-supertag pairs 1526 1497 6288 6044avg. number of parses 6.9 12.7 1166 2939

savings 45.1% 39.7%

features decrease number of results by ≈ 45%

21 / 32

Features restrict adjunction of operators and periphery (1)

SENTENCE

PP-PERI

NP[NUC-O rOPS [NP -]

][NUC-O lOPS [NP -]

]COREN

CLAUSE

NP [NUC-O rOPS [NP -]

][NUC-O lOPS [NP -]

]AP-PERI

industrial

average

DEF-OP

[NUC-O lOPS [NP -]

][NUC-O lOPS [NP +]

Sentence: By 9:45, the industrial average had dropped 27 points.

22 / 32

Features restrict adjunction of operators and periphery (2)

SENTENCE

PP-PERI

CLAUSE

AP-PERI

industrial

average

DEF-OP

Sentence: By 9:45, the industrial average had dropped 27 points.

23 / 32

Outline

Parsing experiments

Issues

Summary & Outlook

24 / 32

Attachment ambiguitiesCORE*

PP-PERI

CORE_P

CORE↓

PP-PERI

CORE_P

CORE_N*

PP-PERI

CORE_P

PP-PERI

CORE_P

CORE↓

CORE-N

PP-PERI

CORE_P

X↓NUC_P

CORE-N

syntactic information needed that might not be in RRGBank25 / 32

Size of the grammar

Gold Grammar Silver Grammarw feats w/o feats w feats w/o feats

Sentences 395 1480avg. sentence length 6.1 8.0token-supertag pairs 1526 1497 6288 6044avg. number of parses 6.9 12.7 1166 2939

the number of parses per sentence increases with the size of the grammar

26 / 32

Extraction of wrapping substitution treesCL

CL↓CO

Asterix

Obelix

Asterix

? discontinuous constituents are marked with traces in PTB;

? no special marking in RRGBank;

? transfer traces from PTB to RRG trees in RRGbank?27 / 32

Outline

Parsing experiments

Issues

Summary & Outlook

28 / 32

Summary

? automatically extracted elementary trees from RRGBank;? experiments with exhaustive parsing of 395/1480 sentences;? parsing w/o edge features → too many results;? some edge features already rule out bad results.

29 / 32

Future Work

? adding more edge features = better results;? extract wrapping elementary trees;? 100s of results → not satisfying;? ambiguity and annotation/extraction mistakes have badconsequences;

? use unlexicalized elementary trees (= supertags);? probabilistic grammar and parsing→ A* parsing algorithm ParTAGe by Waszczuk (2017) [5];

? Web GUI.

30 / 32

Thank you!

THANK YOU VERY MUCH FOR YOUR ATTENTION!

31 / 32

References

References I

Arps, D. and Petitjean, S. (2018). A Parser for LTAG and Frame Semantics. In chair), N. C. C., Choukri, K., Cieri, C.,Declerck, T., Goggi, S., Hasida, K., Isahara, H., Maegaard, B., Mariani, J., Mazo, H., Moreno, A., Odijk, J.,Piperidis, S., and Tokunaga, T., editors, Proceedings of the Eleventh International Conference on LanguageResources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).

Bladier, T., van Cranenburgh, A., Evang, K., Kallmeyer, L., Möllemann, R., and Osswald, R. (2018). RRGbank: a Roleand Reference Grammar Corpus of Syntactic Structures Extracted from the Penn Treebank. In Proceedings ofthe 17th International Workshop on Treebanks and Linguistic Theories (TLT 2018), December 13–14, 2018,Oslo University, Norway, number 155, pages 5–16. Linköping University Electronic Press.

Kallmeyer, L., Osswald, R., and Van Valin, Jr., R. D. (2013). Tree Wrapping for Role and Reference Grammar. In Morrill,G. and Nederhof, M.-J., editors, Formal Grammar 2012/2013, volume 8036 of LNCS, pages 175–190. Springer.

Osswald, R. and Kallmeyer, L. (2018). Towards a formalization of role and reference grammar. In Kailuweit, R., Künkel,L., and Staudinger, E., editors, Applying and Expanding Role and Reference Grammar., pages 355–378.Albert-Ludwigs-Universität, Universitätsbibliothek. [NIHIN studies], Freiburg.

Waszczuk, J. (2017). Leveraging MWEs in practical TAG parsing: towards the best of the two worlds. PhD thesis.

Xia, F. (1999). Extracting tree adjoining grammars from bracketed corpora. In Proceedings of the 5th Natural LanguageProcessing Pacific Rim Symposium (NLPRS-99), pages 398–403.

32 / 32

Chart-based RRG parsing using an automatically extracted RRG …€¦ · CO NUC V think RP Asterix...

Documents

Some nuc . reactors

Nuc Degree Brochure

Nuc Info Day_Iordache.pptx

NUC BOX-1165G7 NUC BOX-1135G7 NUC BOX-1115G4 NUC BOX …

Frunze de Nuc Vika

NOU Canaturi duble cu glisare paralelă NOUEuroinvest Fag Bavaria Vişin Nuc Wenge Deschis Nuc Verona 1 Nuc Verona 2 Nuc Verona 3 Frasin Argintiu Nuc Alb Acacia Auriu Acacia Argintiu

Intel® NUC Board NUC5i5RYB and Intel® NUC Board NUC5i3RYB

WordPress.com · 2016. 10. 24. · 3/3) Ouc . Dcs dc cl. rp 790?J

06 Medicina Nuc

archives.library.illinois.edu · nuc engr nuc engr nuc engr nuc engr fine apts fine arts' fine arts elect eng elect eng airport airport airport airport airport airport timetable from

Nuc hazard!

Tot despre nuc!!!!!!!!!!!!!

Nuc Shereen

Aula 04 - edisciplinas.usp.brAula 04 Bibliogra a: Apresenta˘c~ao Cl audio R. Lucinda FEA-RP/USP Cl audio R. Lucinda FEA-RP/USP Aula 04. Beamer TiKZABNTeXCorretor Ortogr a co no TeXWorks

Natura IMPRESS - Casa Bravocatalog.casabravo.ro/pdf/natura-impress.pdfEuroinvest Fag PORTA Mahon Nuc Stejar Milano 1 Milano 2 Stejar Milano 4 Stejar Milano 5 Nuc Alb Nuc Modena 1 Nuc

Nuc seoul food 2013

Proiect final plantatii nuc

Espectroscopia Ress Mag Nuc

Intel® NUC Board NUC5CPYB and Intel® NUC Board ......iv The Intel NUC Board NUC5CPYB and Intel NUC Board NUC5PPYB may contain design defects or errors known as errata that may cause

N3160-NUC IPC N3710-NUC IPCdownload.asrock.com/IPC/Download/e-catalog/N3710-NUC IPC.pdf · N3160-NUC IPC/ N3710-NUC IPC Storage M.2 mSATA SATA eMMC N/A 1 1 x SATA3 (6Gb/s) N/A Rear