A constrained latent variable model for coreference resolution

Kai Wei Chang, Rajhans Samdani, Dan Roth

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

Abstract

Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning. Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.

Original languageEnglish (US)
Title of host publicationEMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages601-612
Number of pages12
ISBN (Electronic)9781937284978
StatePublished - Jan 1 2013
Event2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013 - Seattle, United States
Duration: Oct 18 2013Oct 21 2013

Publication series

NameEMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Other

Other2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013
CountryUnited States
CitySeattle
Period10/18/1310/21/13

Fingerprint

Processing
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Computer Vision and Pattern Recognition

Cite this

Chang, K. W., Samdani, R., & Roth, D. (2013). A constrained latent variable model for coreference resolution. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 601-612). (EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL).

A constrained latent variable model for coreference resolution. / Chang, Kai Wei; Samdani, Rajhans; Roth, Dan.

EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. p. 601-612 (EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

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

Chang, KW, Samdani, R & Roth, D 2013, A constrained latent variable model for coreference resolution. in EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 601-612, 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Seattle, United States, 10/18/13.
Chang KW, Samdani R, Roth D. A constrained latent variable model for coreference resolution. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2013. p. 601-612. (EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).
Chang, Kai Wei ; Samdani, Rajhans ; Roth, Dan. / A constrained latent variable model for coreference resolution. EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. pp. 601-612 (EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).
@inproceedings{d203d252dfd745438e1e1af227eeb93c,
title = "A constrained latent variable model for coreference resolution",
abstract = "Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning. Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.",
author = "Chang, {Kai Wei} and Rajhans Samdani and Dan Roth",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
series = "EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "601--612",
booktitle = "EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - A constrained latent variable model for coreference resolution

AU - Chang, Kai Wei

AU - Samdani, Rajhans

AU - Roth, Dan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning. Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.

AB - Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning. Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.

UR - http://www.scopus.com/inward/record.url?scp=84902787899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902787899&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84902787899

T3 - EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

SP - 601

EP - 612

BT - EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -