Lexical Features in Coreference Resolution: To be Used With Caution

Nafise Sadat Moosavi, Michael Strube


Abstract
Lexical features are a major source of information in state-of-the-art coreference resolvers. Lexical features implicitly model some of the linguistic phenomena at a fine granularity level. They are especially useful for representing the context of mentions. In this paper we investigate a drawback of using many lexical features in state-of-the-art coreference resolvers. We show that if coreference resolvers mainly rely on lexical features, they can hardly generalize to unseen domains. Furthermore, we show that the current coreference resolution evaluation is clearly flawed by only evaluating on a specific split of a specific dataset in which there is a notable overlap between the training, development and test sets.
Anthology ID:
P17-2003
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–19
Language:
URL:
https://aclanthology.org/P17-2003
DOI:
10.18653/v1/P17-2003
Bibkey:
Cite (ACL):
Nafise Sadat Moosavi and Michael Strube. 2017. Lexical Features in Coreference Resolution: To be Used With Caution. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 14–19, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Lexical Features in Coreference Resolution: To be Used With Caution (Moosavi & Strube, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-2003.pdf
Video:
 https://aclanthology.org/P17-2003.mp4
Data
WikiCoref