Using Type Information to Improve Entity Coreference Resolution

Sopan Khosla, Carolyn Rose


Abstract
Coreference resolution (CR) is an essential part of discourse analysis. Most recently, neural approaches have been proposed to improve over SOTA models from earlier paradigms. So far none of the published neural models leverage external semantic knowledge such as type information. This paper offers the first such model and evaluation, demonstrating modest gains in accuracy by introducing either gold standard or predicted types. In the proposed approach, type information serves both to (1) improve mention representation and (2) create a soft type consistency check between coreference candidate mentions. Our evaluation covers two different grain sizes of types over four different benchmark corpora.
Anthology ID:
2020.codi-1.3
Volume:
Proceedings of the First Workshop on Computational Approaches to Discourse
Month:
November
Year:
2020
Address:
Online
Editors:
Chloé Braud, Christian Hardmeier, Junyi Jessy Li, Annie Louis, Michael Strube
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20–31
Language:
URL:
https://aclanthology.org/2020.codi-1.3
DOI:
10.18653/v1/2020.codi-1.3
Bibkey:
Cite (ACL):
Sopan Khosla and Carolyn Rose. 2020. Using Type Information to Improve Entity Coreference Resolution. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 20–31, Online. Association for Computational Linguistics.
Cite (Informal):
Using Type Information to Improve Entity Coreference Resolution (Khosla & Rose, CODI 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2020.codi-1.3.pdf
Video:
 https://slideslive.com/38939688
Data
GAP Coreference DatasetWikiCoref