Revisiting joint modeling of cross-document entity and event coreference resolution

Shany Barhom; Vered Shwartz; Alon Eirew; Michael Bugert; Nils Reimers; Ido Dagan

Revisiting joint modeling of cross-document entity and event coreference resolution

Shany Barhom, Vered Shwartz, Alon Eirew, Michael Bugert, Nils Reimers, Ido Dagan

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

62 Scopus citations

Abstract

Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to within-document entity coreference, with rather little attention to the other variants. We propose a neural architecture for cross-document coreference resolution. Inspired by Lee et al. (2012), we jointly model entity and event coreference. We represent an event (entity) mention using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures. Our model outperforms the previous state-of-the-art event coreference model on ECB+, while providing the first entity coreference results on this corpus. Our analysis confirms that all our representation elements, including the mention span itself, its context, and the relation to other mentions contribute to the model's success.

Original language	English
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	4179-4189
Number of pages	11
ISBN (Electronic)	9781950737482
State	Published - 2020
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Funding

We would like to thank Jackie Chi Kit Cheung for the insightful comments. This work was supported in part by an Intel ICRI-CI grant, the Israel Science Foundation grant 1951/17, the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1), and a grant from Reverso and Theo Hoffenberg.

Funders	Funder number
DIP	DA 1600/1-1
German-Israeli Project Cooperation
Intel ICRI-CI
Deutsche Forschungsgemeinschaft
Israel Science Foundation	1951/17

Cite this

Barhom, S., Shwartz, V., Eirew, A., Bugert, M., Reimers, N., & Dagan, I. (2020). Revisiting joint modeling of cross-document entity and event coreference resolution. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 4179-4189). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Barhom, Shany ; Shwartz, Vered ; Eirew, Alon et al. / Revisiting joint modeling of cross-document entity and event coreference resolution. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 4179-4189 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{382bcf4f07b04f62bb6a5775bc6b7ee4,

title = "Revisiting joint modeling of cross-document entity and event coreference resolution",

abstract = "Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to within-document entity coreference, with rather little attention to the other variants. We propose a neural architecture for cross-document coreference resolution. Inspired by Lee et al. (2012), we jointly model entity and event coreference. We represent an event (entity) mention using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures. Our model outperforms the previous state-of-the-art event coreference model on ECB+, while providing the first entity coreference results on this corpus. Our analysis confirms that all our representation elements, including the mention span itself, its context, and the relation to other mentions contribute to the model's success.",

author = "Shany Barhom and Vered Shwartz and Alon Eirew and Michael Bugert and Nils Reimers and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2020",

language = "אנגלית",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "4179--4189",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "ארצות הברית",

}

Barhom, S, Shwartz, V, Eirew, A, Bugert, M, Reimers, N & Dagan, I 2020, Revisiting joint modeling of cross-document entity and event coreference resolution. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 4179-4189, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28/07/19.

Revisiting joint modeling of cross-document entity and event coreference resolution. / Barhom, Shany; Shwartz, Vered; Eirew, Alon et al.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 4179-4189 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Revisiting joint modeling of cross-document entity and event coreference resolution

AU - Barhom, Shany

AU - Shwartz, Vered

AU - Eirew, Alon

AU - Bugert, Michael

AU - Reimers, Nils

AU - Dagan, Ido

PY - 2020

Y1 - 2020

N2 - Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to within-document entity coreference, with rather little attention to the other variants. We propose a neural architecture for cross-document coreference resolution. Inspired by Lee et al. (2012), we jointly model entity and event coreference. We represent an event (entity) mention using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures. Our model outperforms the previous state-of-the-art event coreference model on ECB+, while providing the first entity coreference results on this corpus. Our analysis confirms that all our representation elements, including the mention span itself, its context, and the relation to other mentions contribute to the model's success.

AB - Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to within-document entity coreference, with rather little attention to the other variants. We propose a neural architecture for cross-document coreference resolution. Inspired by Lee et al. (2012), we jointly model entity and event coreference. We represent an event (entity) mention using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures. Our model outperforms the previous state-of-the-art event coreference model on ECB+, while providing the first entity coreference results on this corpus. Our analysis confirms that all our representation elements, including the mention span itself, its context, and the relation to other mentions contribute to the model's success.

UR - http://www.scopus.com/inward/record.url?scp=85084088162&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85084088162

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 4179

EP - 4189

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Barhom S, Shwartz V, Eirew A, Bugert M, Reimers N, Dagan I. Revisiting joint modeling of cross-document entity and event coreference resolution. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 4179-4189. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Revisiting joint modeling of cross-document entity and event coreference resolution

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this