Collaborative partitioning for coreference resolution

Olga Uryupina, Alessandro Moschitti

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

1 Citation (Scopus)

Abstract

This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific similarity measure. Our approach assumes a loose integration of individual components of the ensemble and can therefore combine arbitrary coreference resolvers, regardless of their models. Our experiments on the CoNLL dataset show that collaborative partitioning yields results superior to those attained by the individual components, for ensembles of both strong and weak systems. Moreover, by applying the collaborative partitioning algorithm on top of three state-of-the-art resolvers, we obtain the second-best coreference performance reported so far in the literature (MELA v08 score of 64.47).

Original languageEnglish
Title of host publicationCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages47-57
Number of pages11
ISBN (Electronic)9781945626548
Publication statusPublished - 1 Jan 2017
Event21st Conference on Computational Natural Language Learning, CoNLL 2017 - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017

Publication series

NameCoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

Conference

Conference21st Conference on Computational Natural Language Learning, CoNLL 2017
CountryCanada
CityVancouver
Period3/8/174/8/17

Fingerprint

experiment
performance
Experiments
literature

ASJC Scopus subject areas

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Uryupina, O., & Moschitti, A. (2017). Collaborative partitioning for coreference resolution. In CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings (pp. 47-57). (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings). Association for Computational Linguistics (ACL).

Collaborative partitioning for coreference resolution. / Uryupina, Olga; Moschitti, Alessandro.

CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 47-57 (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).

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

Uryupina, O & Moschitti, A 2017, Collaborative partitioning for coreference resolution. in CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings, Association for Computational Linguistics (ACL), pp. 47-57, 21st Conference on Computational Natural Language Learning, CoNLL 2017, Vancouver, Canada, 3/8/17.
Uryupina O, Moschitti A. Collaborative partitioning for coreference resolution. In CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 47-57. (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).
Uryupina, Olga ; Moschitti, Alessandro. / Collaborative partitioning for coreference resolution. CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 47-57 (CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings).
@inproceedings{1d3ffb8113de42d49f58da6d399ea106,
title = "Collaborative partitioning for coreference resolution",
abstract = "This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific similarity measure. Our approach assumes a loose integration of individual components of the ensemble and can therefore combine arbitrary coreference resolvers, regardless of their models. Our experiments on the CoNLL dataset show that collaborative partitioning yields results superior to those attained by the individual components, for ensembles of both strong and weak systems. Moreover, by applying the collaborative partitioning algorithm on top of three state-of-the-art resolvers, we obtain the second-best coreference performance reported so far in the literature (MELA v08 score of 64.47).",
author = "Olga Uryupina and Alessandro Moschitti",
year = "2017",
month = "1",
day = "1",
language = "English",
series = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "47--57",
booktitle = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",

}

TY - GEN

T1 - Collaborative partitioning for coreference resolution

AU - Uryupina, Olga

AU - Moschitti, Alessandro

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific similarity measure. Our approach assumes a loose integration of individual components of the ensemble and can therefore combine arbitrary coreference resolvers, regardless of their models. Our experiments on the CoNLL dataset show that collaborative partitioning yields results superior to those attained by the individual components, for ensembles of both strong and weak systems. Moreover, by applying the collaborative partitioning algorithm on top of three state-of-the-art resolvers, we obtain the second-best coreference performance reported so far in the literature (MELA v08 score of 64.47).

AB - This paper presents a collaborative partitioning algorithm—a novel ensemble-based approach to coreference resolution. Starting from the all-singleton partition, we search for a solution close to the ensemble’s outputs in terms of a task-specific similarity measure. Our approach assumes a loose integration of individual components of the ensemble and can therefore combine arbitrary coreference resolvers, regardless of their models. Our experiments on the CoNLL dataset show that collaborative partitioning yields results superior to those attained by the individual components, for ensembles of both strong and weak systems. Moreover, by applying the collaborative partitioning algorithm on top of three state-of-the-art resolvers, we obtain the second-best coreference performance reported so far in the literature (MELA v08 score of 64.47).

UR - http://www.scopus.com/inward/record.url?scp=85050886809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050886809&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85050886809

T3 - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

SP - 47

EP - 57

BT - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -