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

Jiawei Chen, Hongyu Lin, Xianpei Han, Le Sun

2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing20 citationsDOI Open Access PDF

Abstract

Event detection has long been troubled by the 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.

Topics & Concepts

OverfittingComputer scienceContext (archaeology)Machine learningEvent (particle physics)Artificial intelligenceHarmCurseGeneralizationComputer securityPsychologyMathematicsArtificial neural networkSocial psychologyMathematical analysisBiologyQuantum mechanicsPhysicsAnthropologyPaleontologySociologyTopic ModelingAnomaly Detection Techniques and ApplicationsDomain Adaptation and Few-Shot Learning