Pairwise Representation Learning for Event Coreference

Xiaodong Yu, Wenpeng Yin, Dan Roth


Abstract
Natural Language Processing tasks such as resolving the coreference of events require understanding the relations between two text snippets. These tasks are typically formulated as (binary) classification problems over independently induced representations of the text snippets. In this work, we develop a Pairwise Representation Learning (PairwiseRL) scheme for the event mention pairs, in which we jointly encode a pair of text snippets so that the representation of each mention in the pair is induced in the context of the other one. Furthermore, our representation supports a finer, structured representation of the text snippet to facilitate encoding events and their arguments. We show that PairwiseRL, despite its simplicity, outperforms the prior state-of-the-art event coreference systems on both cross-document and within-document event coreference benchmarks. We also conduct in-depth analysis in terms of the improvement and the limitation of pairwise representation so as to provide insights for future work.
Anthology ID:
2022.starsem-1.6
Volume:
Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
Month:
July
Year:
2022
Address:
Seattle, Washington
Editors:
Vivi Nastase, Ellie Pavlick, Mohammad Taher Pilehvar, Jose Camacho-Collados, Alessandro Raganato
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–78
Language:
URL:
https://aclanthology.org/2022.starsem-1.6
DOI:
10.18653/v1/2022.starsem-1.6
Bibkey:
Cite (ACL):
Xiaodong Yu, Wenpeng Yin, and Dan Roth. 2022. Pairwise Representation Learning for Event Coreference. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 69–78, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Pairwise Representation Learning for Event Coreference (Yu et al., *SEM 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.starsem-1.6.pdf
Data
ECB+