research-article

Free access

Semi-supervised semantic role labeling

Authors:

Hagen Fürstenau,

Mirella LapataAuthors Info & Claims

EACL '09: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

Pages 220 - 228

Published: 30 March 2009 Publication History

Abstract

Large scale annotated corpora are prerequisite to developing high-performance semantic role labeling systems. Unfortunately, such corpora are expensive to produce, limited in size, and may not be representative. Our work aims to reduce the annotation effort involved in creating resources for semantic role labeling via semi-supervised learning. Our algorithm augments a small number of manually labeled instances with unlabeled examples whose roles are inferred automatically via annotation projection. We formulate the projection task as a generalization of the linear assignment problem. We seek to find a role assignment in the unlabeled data such that the argument similarity between the labeled and unlabeled instances is maximized. Experimental results on semantic role labeling show that the automatic annotations produced by our method improve performance over using hand-labeled instances alone.

References

[1]

Collin F. Baker, Michael Ellsworth, and Katrin Erk. 2007. SemEval-2007 Task 19: Frame Semantic Structure Extraction. In Proceedings of the 4th International Workshop on Semantic Evaluations, pages 99--104, Prague, Czech Republic.

Digital Library

[2]

R. P. Brent. 1973. Algorithms for Minimization without Derivatives. Prentice-Hall, Englewood Cliffs, NJ.

[3]

Ted Briscoe, John Carroll, and Rebecca Watson. 2006. The Second Release of the RASP System. In Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions, pages 77--80, Sydney, Australia.

Digital Library

[4]

J. A. Bullinaria and J. P. Levy. 2007. Extracting semantic representations from word co-occurrence statistics: A computational study. Behavior Research Methods, 39:510--526.

[5]

George B. Dantzig. 1963. Linear Programming and Extensions. Princeton University Press, Princeton, NJ, USA.

[6]

R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. 2008. Lib Linear: A library for large linear classification. Journal of Machine Learning Research, 9:1871--1874.

Digital Library

[7]

Charles J. Fillmore, Christopher R. Johnson, and Miriam R. L. Petruck. 2003. Background to FrameNet. International Journal of Lexicography, 16:235--250.

[8]

Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Eytan Ruppin. 2002. Placing search in context: The concept revisited. ACM Transactions on Information Systems, 20(1):116--131.

Digital Library

[9]

Jerome H. Friedman. 1996. Another approach to polychotomous classification. Technical report. Department of Statistics, Stanford University.

[10]

Pascale Fung and Benfeng Chen. 2004. BiFrameNet: Bilingual frame semantics resources construction by cross-lingual induction. In Proceedings of the 20th International Conference on Computational Linguistics, pages 931--935, Geneva, Switzerland.

Digital Library

[11]

Hagen Fürstenau. 2008. Enriching frame semantic resources with dependency graphs. In Proceedings of the 6th Language Resources and Evaluation Conference, Marrakech, Morocco.

[12]

Daniel Gildea and Dan Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28:3:245--288.

Digital Library

[13]

Andrew Gordon and Reid Swanson. 2007. Generalizing semantic role annotations across syntactically similar verbs. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 192--199, Prague, Czech Republic.

[14]

Richard Johansson and Pierre Nugues. 2006. A FrameNet-based semantic role labeler for Swedish. In Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 436--443, Sydney, Australia.

Digital Library

[15]

Richard Johansson and Pierre Nugues. 2008. The effect of syntactic representation on semantic role labeling. In Proceedings of the 22nd International Conference on Computational Linguistics, pages 393--400, Manchester, UK.

Digital Library

[16]

Beth Levin. 1993. English Verb Classes and Alternations: A Preliminary Investigation. University of Chicago Press.

[17]

Alessandro Moschitti, Paul Morarescu, and Sanda Harabagiu. 2003. Open-domain information extraction via automatic semantic labeling. In Proceedings of FLAIRS 2003, pages 397--401, St. Augustine, FL.

[18]

E. Noreen. 1989. Computer-intensive Methods for Testing Hypotheses: An Introduction. John Wiley and Sons Inc.

[19]

Sebastian Padó and Katrin Erk. 2005. To cause or not to cause: Cross-lingual semantic matching for paraphrase modelling. In Proceedings of the EUROLAN Workshop on Cross-Linguistic Knowledge Induction, pages 23--30, Cluj-Napoca, Romania.

[20]

Sebastian Padó and Mirella Lapata. 2006. Optimal constituent alignment with edge covers for semantic projection. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 1161--1168, Sydney, Australia.

Digital Library

[21]

Martha Palmer. Dan Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71--106.

Digital Library

[22]

Marco Pennacchiotti, Diego De Cao, Roberto Basili, Danilo Croce, and Michael Roth. 2008. Automatic induction of FrameNet lexical units. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 457--465, Honolulu, Hawaii.

Digital Library

[23]

Dan Shen and Mirella Lapata. 2007. Using semantic roles to improve question answering. In Proceedings of the joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning, pages 12--21, Prague, Czech Republic.

[24]

Mihai Surdeanu, Sanda Harabagiu, John Williams, and Paul Aarseth. 2003. Using predicate-argument structures for information extraction. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 8--15, Sapporo, Japan.

Digital Library

[25]

Robert S. Swier and Suzanne Stevenson. 2004. Unsupervised semantic role labelling. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 95--102. Bacelona. Spain.

[26]

Marta Tatu and Dan Moldovan. 2005. A semantic approach to recognizing textual entailment. In Proceedings of the joint Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 371--378, Vancouver, BC.

Digital Library

Cited By

Huang FAhuja ADowney DYang YGuo YYates A(2014)Learning representations for weakly supervised natural language processing tasksComputational Linguistics10.1162/COLI_a_0016740:1(85-120)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1162/COLI_a_00167
Das DChen DMartins ASchneider NSmith N(2014)Frame-semantic parsingComputational Linguistics10.1162/COLI_a_0016340:1(9-56)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1162/COLI_a_00163
Borin LDubhashi DForsberg MJohansson RKokkinakis DNugues PLiu XChen MDing YSong M(2013)Mining semantics for culturomicsProceedings of the 2013 international workshop on Mining unstructured big data using natural language processing10.1145/2513549.2513551(3-10)Online publication date: 28-Oct-2013
https://dl.acm.org/doi/10.1145/2513549.2513551
Show More Cited By

Index Terms

Semi-supervised semantic role labeling
1. Computing methodologies

Recommendations

Investigation of Weakly Supervised Learning for Semantic Role Labeling
ALPIT '07: Proceedings of the Sixth International Conference on Advanced Language Processing and Web Information Technology (ALPIT 2007)

In this paper, we investigate the possibility of the weakly supervised learning for Semantic Role Labeling. First, we attempt to achieve feature splitting which is the base constraint of co-training, and examine if co-training works for the task of ...
Sentiment labeling for extending initial labeled data to improve semi-supervised sentiment classification

Semi-supervised framework which exploits unsupervised approach (JST) is proposed.Self-training suffers from incorrectly labeling problem with insufficient data.Confidently predicted instances are labeled and used as training data by JST.Self-training ...
Unsupervised Selective Labeling for More Effective Semi-supervised Learning
Computer Vision – ECCV 2022
Abstract
Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right data ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

EACL '09: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

March 2009

905 pages

General Chair:
Alex Lascarides
University of Edinburgh (UK)
,
Program Chairs:
Claire Gardent
CNRS/LORIA Nancy (France)
,
Joakim Nivre
Uppsala University and Vaxjo University (Sweden)

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 30 March 2009

Qualifiers

Research-article

Acceptance Rates

EACL '09 Paper Acceptance Rate 100 of 360 submissions, 28%;

Overall Acceptance Rate 100 of 360 submissions, 28%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
362
Total Downloads

Downloads (Last 12 months)47
Downloads (Last 6 weeks)11

Reflects downloads up to 13 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Huang FAhuja ADowney DYang YGuo YYates A(2014)Learning representations for weakly supervised natural language processing tasksComputational Linguistics10.1162/COLI_a_0016740:1(85-120)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1162/COLI_a_00167
Das DChen DMartins ASchneider NSmith N(2014)Frame-semantic parsingComputational Linguistics10.1162/COLI_a_0016340:1(9-56)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1162/COLI_a_00163
Borin LDubhashi DForsberg MJohansson RKokkinakis DNugues PLiu XChen MDing YSong M(2013)Mining semantics for culturomicsProceedings of the 2013 international workshop on Mining unstructured big data using natural language processing10.1145/2513549.2513551(3-10)Online publication date: 28-Oct-2013
https://dl.acm.org/doi/10.1145/2513549.2513551
Gilpin SEliassi-Rad TDavidson IGrossman RUthurusamy RDhillon IKoren Y(2013)Guided learning for role discovery (GLRD)Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining10.1145/2487575.2487620(113-121)Online publication date: 11-Aug-2013
https://dl.acm.org/doi/10.1145/2487575.2487620
Henderson KGallagher BEliassi-Rad TTong HBasu SAkoglu LKoutra DFaloutsos CLi LYang QAgarwal DPei J(2012)RolXProceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining10.1145/2339530.2339723(1231-1239)Online publication date: 12-Aug-2012
https://dl.acm.org/doi/10.1145/2339530.2339723
Alva-Manchego FRosa J(2012)Towards semi-supervised brazilian portuguese semantic role labelingProceedings of the 10th international conference on Computational Processing of the Portuguese Language10.1007/978-3-642-28885-2_24(210-217)Online publication date: 17-Apr-2012
https://dl.acm.org/doi/10.1007/978-3-642-28885-2_24
Yu NKübler SGoldwater SManning C(2011)Filling the gapProceedings of the Fifteenth Conference on Computational Natural Language Learning10.5555/2018936.2018959(200-209)Online publication date: 23-Jun-2011
https://dl.acm.org/doi/10.5555/2018936.2018959
Das DSmith NLin D(2011)Semi-supervised frame-semantic parsing for unknown predicatesProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 110.5555/2002472.2002648(1435-1444)Online publication date: 19-Jun-2011
https://dl.acm.org/doi/10.5555/2002472.2002648
Palmer ASporleder CJoshi AHuang CJurafsky D(2010)Evaluating FrameNet-style semantic parsingProceedings of the 23rd International Conference on Computational Linguistics: Posters10.5555/1944566.1944673(928-936)Online publication date: 23-Aug-2010
https://dl.acm.org/doi/10.5555/1944566.1944673
Huang FYates AHajič J(2010)Open-domain semantic role labeling by modeling word spansProceedings of the 48th Annual Meeting of the Association for Computational Linguistics10.5555/1858681.1858780(968-978)Online publication date: 11-Jul-2010
https://dl.acm.org/doi/10.5555/1858681.1858780
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents