Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention

TL;DR

This paper addresses the trigger curse in few-shot event detection by using causal intervention to improve generalization and detection performance across multiple datasets.

Contribution

It introduces a causal model-based approach with backdoor adjustment to mitigate trigger overfitting in few-shot event detection.

Findings

Significant performance improvements on ACE05, MAVEN, and KBP17 datasets.

Causal intervention effectively reduces trigger overfitting.

Enhanced generalization in few-shot event detection scenarios.

Abstract

Event detection has long been troubled by the \emph{trigger curse}: overfitting the trigger will harm the generalization ability while underfitting it will hurt the detection performance. This problem is even more severe in few-shot scenario. In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view. By formulating FSED with a structural causal model (SCM), we found that the trigger is a confounder of the context and the result, which makes previous FSED methods much easier to overfit triggers. To resolve this problem, we propose to intervene on the context via backdoor adjustment during training. Experiments show that our method significantly improves the FSED on ACE05, MAVEN and KBP17 datasets.