HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold

Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, Dangyang Chen


Abstract
Event detection has been suffering from constantly emerging event types with lack of sufficient data. Existing works formulate the new problem as few-shot event detection (FSED), and employ two-stage or unified models based on meta-learning to address the problem. However, these methods fall far short of expectations due to: (i) insufficient learning of discriminative representations in low-resource scenarios, and (ii) representation overlap between triggers and non-triggers. To resolve the above issues, in this paper, we propose a novel Hybrid Contrastive Learning method with a Task-Adaptive Threshold (abbreviated as HCL-TAT), which enables discriminative representation learning with a two-view contrastive loss (support-support and prototype-query), and devises an easily-adapted threshold to alleviate misidentification of triggers. Extensive experiments on the benchmark dataset FewEvent demonstrate the superiority of our method to achieve better results compared to the state-of-the-arts. All the data and codes will be available to facilitate future research.
Anthology ID:
2022.findings-emnlp.130
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1808–1819
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.130
DOI:
10.18653/v1/2022.findings-emnlp.130
Bibkey:
Cite (ACL):
Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, and Dangyang Chen. 2022. HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1808–1819, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold (Zhang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.130.pdf