On Generalization in Coreference Resolution

Shubham Toshniwal, Patrick Xia, Sam Wiseman, Karen Livescu, Kevin Gimpel


Abstract
While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.
Anthology ID:
2021.crac-1.12
Volume:
Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
CRAC | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
111–120
Language:
URL:
https://aclanthology.org/2021.crac-1.12
DOI:
10.18653/v1/2021.crac-1.12
Bibkey:
Cite (ACL):
Shubham Toshniwal, Patrick Xia, Sam Wiseman, Karen Livescu, and Kevin Gimpel. 2021. On Generalization in Coreference Resolution. In Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 111–120, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
On Generalization in Coreference Resolution (Toshniwal et al., CRAC 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.crac-1.12.pdf
Code
 shtoshni92/fast-coref
Data
GAP Coreference DatasetOntoGUMPreCoWSCWikiCoref