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

TL;DR

This paper introduces HCL-TAT, a hybrid contrastive learning approach with a task-adaptive threshold for improved few-shot event detection, addressing low-resource representation learning and trigger misidentification issues.

Contribution

It proposes a novel hybrid contrastive learning framework with a task-adaptive threshold to enhance discriminative features and trigger identification in few-shot event detection.

Findings

Outperforms state-of-the-art methods on FewEvent dataset

Effective in low-resource scenarios for event detection

Reduces trigger misidentification through adaptive thresholding

Abstract

Conventional event detection models under supervised learning settings suffer from the inability of transfer to newly-emerged event types owing to lack of sufficient annotations. A commonly-adapted solution is to follow a identify-then-classify manner, which first identifies the triggers and then converts the classification task via a few-shot learning paradigm. However, these methods still fall far short of expectations due to: (i) insufficient learning of discriminative representations in low-resource scenarios, and (ii) trigger misidentification caused by the overlap of the learned representations of triggers and non-triggers. To address the problems, in this paper, we propose a novel Hybrid Contrastive Learning method with a Task-Adaptive Threshold (abbreviated as HCLTAT), which enables discriminative representation learning with a two-view contrastive loss (support-support and prototype-query), and devises a 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 code and data of this paper will be available for online public access.