Moosavi, N.S. orcid.org/0000-0002-8332-307X and Strube, M. (2018) Using linguistic features to improve the generalization capability of neural coreference resolvers. In: Riloff, E., Chiang, D., Hockenmaier, J. and Tsujii, J., (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), 31 Oct - 04 Nov 2018, Brussels, Belgium. Association for Computational Linguistics , pp. 193-203. ISBN 9781948087841
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.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2018 Association for Computational Linguistics. Available under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 07 Sep 2022 16:06 |
Last Modified: | 07 Sep 2022 16:06 |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/D18-1018 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190605 |