Joint entity and event coreference resolution across documents

Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, Dan Jurafsky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

76 Citations (Scopus)

Abstract

We introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built, information flows between entity and event clusters through features that model semantic role dependencies. Our system handles nominal and verbal events as well as entities, and our joint formulation allows information from event coreference to help entity coreference, and vice versa. In a cross-document domain with comparable documents, joint coreference resolution performs significantly better (over 3 CoNLL F1 points) than two strong baselines that resolve entities and events separately.

Original languageEnglish (US)
Title of host publicationEMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference
Pages489-500
Number of pages12
StatePublished - 2012
Externally publishedYes
Event2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Jeju Island, Korea, Republic of
Duration: Jul 12 2012Jul 14 2012

Other

Other2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012
CountryKorea, Republic of
CityJeju Island
Period7/12/127/14/12

Fingerprint

Iterative methods
Linear regression
Semantics

ASJC Scopus subject areas

  • Software

Cite this

Lee, H., Recasens, M., Chang, A., Surdeanu, M., & Jurafsky, D. (2012). Joint entity and event coreference resolution across documents. In EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference (pp. 489-500)

Joint entity and event coreference resolution across documents. / Lee, Heeyoung; Recasens, Marta; Chang, Angel; Surdeanu, Mihai; Jurafsky, Dan.

EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. p. 489-500.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, H, Recasens, M, Chang, A, Surdeanu, M & Jurafsky, D 2012, Joint entity and event coreference resolution across documents. in EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. pp. 489-500, 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012, Jeju Island, Korea, Republic of, 7/12/12.
Lee H, Recasens M, Chang A, Surdeanu M, Jurafsky D. Joint entity and event coreference resolution across documents. In EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. p. 489-500
Lee, Heeyoung ; Recasens, Marta ; Chang, Angel ; Surdeanu, Mihai ; Jurafsky, Dan. / Joint entity and event coreference resolution across documents. EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference. 2012. pp. 489-500
@inproceedings{80c3e113499f4e64b8df28a124793411,
title = "Joint entity and event coreference resolution across documents",
abstract = "We introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built, information flows between entity and event clusters through features that model semantic role dependencies. Our system handles nominal and verbal events as well as entities, and our joint formulation allows information from event coreference to help entity coreference, and vice versa. In a cross-document domain with comparable documents, joint coreference resolution performs significantly better (over 3 CoNLL F1 points) than two strong baselines that resolve entities and events separately.",
author = "Heeyoung Lee and Marta Recasens and Angel Chang and Mihai Surdeanu and Dan Jurafsky",
year = "2012",
language = "English (US)",
isbn = "9781937284435",
pages = "489--500",
booktitle = "EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference",

}

TY - GEN

T1 - Joint entity and event coreference resolution across documents

AU - Lee, Heeyoung

AU - Recasens, Marta

AU - Chang, Angel

AU - Surdeanu, Mihai

AU - Jurafsky, Dan

PY - 2012

Y1 - 2012

N2 - We introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built, information flows between entity and event clusters through features that model semantic role dependencies. Our system handles nominal and verbal events as well as entities, and our joint formulation allows information from event coreference to help entity coreference, and vice versa. In a cross-document domain with comparable documents, joint coreference resolution performs significantly better (over 3 CoNLL F1 points) than two strong baselines that resolve entities and events separately.

AB - We introduce a novel coreference resolution system that models entities and events jointly. Our iterative method cautiously constructs clusters of entity and event mentions using linear regression to model cluster merge operations. As clusters are built, information flows between entity and event clusters through features that model semantic role dependencies. Our system handles nominal and verbal events as well as entities, and our joint formulation allows information from event coreference to help entity coreference, and vice versa. In a cross-document domain with comparable documents, joint coreference resolution performs significantly better (over 3 CoNLL F1 points) than two strong baselines that resolve entities and events separately.

UR - http://www.scopus.com/inward/record.url?scp=84881101926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881101926&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284435

SP - 489

EP - 500

BT - EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

ER -