Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering

Jun Gao, Wei Wang, Changlong Yu, Huan Zhao, Wilfred Ng, Ruifeng Xu


Abstract
Representations of events described in text are important for various tasks. In this work, we present SWCC: a Simultaneous Weakly supervised Contrastive learning and Clustering framework for event representation learning. SWCC learns event representations by making better use of co-occurrence information of events. Specifically, we introduce a weakly supervised contrastive learning method that allows us to consider multiple positives and multiple negatives, and a prototype-based clustering method that avoids semantically related events being pulled apart. For model training, SWCC learns representations by simultaneously performing weakly supervised contrastive learning and prototype-based clustering. Experimental results show that SWCC outperforms other baselines on Hard Similarity and Transitive Sentence Similarity tasks. In addition, a thorough analysis of the prototype-based clustering method demonstrates that the learned prototype vectors are able to implicitly capture various relations between events.
Anthology ID:
2022.acl-long.216
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3036–3049
Language:
URL:
https://aclanthology.org/2022.acl-long.216
DOI:
10.18653/v1/2022.acl-long.216
Bibkey:
Cite (ACL):
Jun Gao, Wei Wang, Changlong Yu, Huan Zhao, Wilfred Ng, and Ruifeng Xu. 2022. Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3036–3049, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering (Gao et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.216.pdf
Software:
 2022.acl-long.216.software.zip
Code
 gaojun4ever/swcc4event