Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers

Nafise Sadat Moosavi, Michael Strube


Abstract
Coreference resolution is an intermediate step for text understanding. It is used in tasks and domains for which we do not necessarily have coreference annotated corpora. Therefore, generalization is of special importance for coreference resolution. However, while recent coreference resolvers have notable improvements on the CoNLL dataset, they struggle to generalize properly to new domains or datasets. In this paper, we investigate the role of linguistic features in building more generalizable coreference resolvers. We show that generalization improves only slightly by merely using a set of additional linguistic features. However, employing features and subsets of their values that are informative for coreference resolution, considerably improves generalization. Thanks to better generalization, our system achieves state-of-the-art results in out-of-domain evaluations, e.g., on WikiCoref, our system, which is trained on CoNLL, achieves on-par performance with a system designed for this dataset.
Anthology ID:
D18-1018
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
193–203
Language:
URL:
https://aclanthology.org/D18-1018
DOI:
10.18653/v1/D18-1018
Bibkey:
Cite (ACL):
Nafise Sadat Moosavi and Michael Strube. 2018. Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 193–203, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers (Moosavi & Strube, EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/D18-1018.pdf
Attachment:
 D18-1018.Attachment.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/D18-1018.mp4
Code
 ns-moosavi/epm
Data
WikiCoref