Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance

Sopan Khosla, James Fiacco, Carolyn Rosé


Abstract
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features. SOTA models do not make use of hierarchical representations of discourse structure. In this work, we leverage automatically constructed discourse parse trees within a neural approach and demonstrate a significant improvement on two benchmark entity coreference-resolution datasets. We explore how the impact varies depending upon the type of mention.
Anthology ID:
2021.naacl-main.130
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1645–1651
Language:
URL:
https://aclanthology.org/2021.naacl-main.130
DOI:
10.18653/v1/2021.naacl-main.130
Bibkey:
Cite (ACL):
Sopan Khosla, James Fiacco, and Carolyn Rosé. 2021. Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1645–1651, Online. Association for Computational Linguistics.
Cite (Informal):
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance (Khosla et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2021.naacl-main.130.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2021.naacl-main.130.mp4