Exophoric Pronoun Resolution in Dialogues with Topic Regularization

Xintong Yu, Hongming Zhang, Yangqiu Song, Changshui Zhang, Kun Xu, Dong Yu


Abstract
Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exophoric scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.
Anthology ID:
2021.emnlp-main.311
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3832–3845
Language:
URL:
https://aclanthology.org/2021.emnlp-main.311
DOI:
10.18653/v1/2021.emnlp-main.311
Bibkey:
Cite (ACL):
Xintong Yu, Hongming Zhang, Yangqiu Song, Changshui Zhang, Kun Xu, and Dong Yu. 2021. Exophoric Pronoun Resolution in Dialogues with Topic Regularization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3832–3845, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Exophoric Pronoun Resolution in Dialogues with Topic Regularization (Yu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.311.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.311.mp4
Code
 hkust-knowcomp/exo-pcr
Data
VisPro