A state-of-the-art mention-pair model for coreference resolution

Olga Uryupina, Alessandro Moschitti

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

2 Citations (Scopus)

Abstract

Most recent studies on coreference resolution advocate accurate yet relatively complex models, relying on, for example, entitymention or graph-based representations. As it has been convincingly demonstrated at the recent CoNLL 2012 shared task, such algorithms considerably outperform popular basic approaches, in particular mention-pair models. This study advocates a novel approach that keeps the simplicity of a mention-pair framework, while showing state-of-the-art results. Apart from being very efficient and straightforward to implement, our model facilitates experimental work on the pairwise classifier, in particular on feature engineering. The proposed model achieves the performance level of up to 61.82% (MELA F, v4 scorer) on the CoNLL test data, on par with complex state-of-the-art systems.

Original languageEnglish
Title of host publicationProceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
PublisherAssociation for Computational Linguistics (ACL)
Pages289-298
Number of pages10
ISBN (Electronic)9781941643396
Publication statusPublished - 1 Jan 2015
Event4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 - Denver, United States
Duration: 4 Jun 20155 Jun 2015

Other

Other4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
CountryUnited States
CityDenver
Period4/6/155/6/15

Fingerprint

Classifiers

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Uryupina, O., & Moschitti, A. (2015). A state-of-the-art mention-pair model for coreference resolution. In Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 (pp. 289-298). Association for Computational Linguistics (ACL).

A state-of-the-art mention-pair model for coreference resolution. / Uryupina, Olga; Moschitti, Alessandro.

Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015. Association for Computational Linguistics (ACL), 2015. p. 289-298.

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

Uryupina, O & Moschitti, A 2015, A state-of-the-art mention-pair model for coreference resolution. in Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015. Association for Computational Linguistics (ACL), pp. 289-298, 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015, Denver, United States, 4/6/15.
Uryupina O, Moschitti A. A state-of-the-art mention-pair model for coreference resolution. In Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015. Association for Computational Linguistics (ACL). 2015. p. 289-298
Uryupina, Olga ; Moschitti, Alessandro. / A state-of-the-art mention-pair model for coreference resolution. Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015. Association for Computational Linguistics (ACL), 2015. pp. 289-298
@inproceedings{cf7794f516ec4ba187d838493ce1d2ea,
title = "A state-of-the-art mention-pair model for coreference resolution",
abstract = "Most recent studies on coreference resolution advocate accurate yet relatively complex models, relying on, for example, entitymention or graph-based representations. As it has been convincingly demonstrated at the recent CoNLL 2012 shared task, such algorithms considerably outperform popular basic approaches, in particular mention-pair models. This study advocates a novel approach that keeps the simplicity of a mention-pair framework, while showing state-of-the-art results. Apart from being very efficient and straightforward to implement, our model facilitates experimental work on the pairwise classifier, in particular on feature engineering. The proposed model achieves the performance level of up to 61.82{\%} (MELA F, v4 scorer) on the CoNLL test data, on par with complex state-of-the-art systems.",
author = "Olga Uryupina and Alessandro Moschitti",
year = "2015",
month = "1",
day = "1",
language = "English",
pages = "289--298",
booktitle = "Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - A state-of-the-art mention-pair model for coreference resolution

AU - Uryupina, Olga

AU - Moschitti, Alessandro

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Most recent studies on coreference resolution advocate accurate yet relatively complex models, relying on, for example, entitymention or graph-based representations. As it has been convincingly demonstrated at the recent CoNLL 2012 shared task, such algorithms considerably outperform popular basic approaches, in particular mention-pair models. This study advocates a novel approach that keeps the simplicity of a mention-pair framework, while showing state-of-the-art results. Apart from being very efficient and straightforward to implement, our model facilitates experimental work on the pairwise classifier, in particular on feature engineering. The proposed model achieves the performance level of up to 61.82% (MELA F, v4 scorer) on the CoNLL test data, on par with complex state-of-the-art systems.

AB - Most recent studies on coreference resolution advocate accurate yet relatively complex models, relying on, for example, entitymention or graph-based representations. As it has been convincingly demonstrated at the recent CoNLL 2012 shared task, such algorithms considerably outperform popular basic approaches, in particular mention-pair models. This study advocates a novel approach that keeps the simplicity of a mention-pair framework, while showing state-of-the-art results. Apart from being very efficient and straightforward to implement, our model facilitates experimental work on the pairwise classifier, in particular on feature engineering. The proposed model achieves the performance level of up to 61.82% (MELA F, v4 scorer) on the CoNLL test data, on par with complex state-of-the-art systems.

UR - http://www.scopus.com/inward/record.url?scp=85021841930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021841930&partnerID=8YFLogxK

M3 - Conference contribution

SP - 289

EP - 298

BT - Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015

PB - Association for Computational Linguistics (ACL)

ER -