Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection

TL;DR

This paper introduces an adaptive Bayesian meta-learning approach that leverages external event knowledge to improve few-shot event detection, significantly outperforming existing methods in low-data scenarios.

Contribution

It proposes a novel knowledge-based few-shot event detection method with an adaptive Bayesian framework to dynamically incorporate external knowledge as a prior.

Findings

Outperforms baselines by at least 15 F1 points in few-shot settings.

Effectively incorporates external knowledge to enhance event detection.

Demonstrates robustness to limited and imperfect external knowledge.

Abstract

Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem. To tackle the issue of low sample diversity in few-shot ED, we propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge as the knowledge prior of event types. Furthermore, as external knowledge typically provides limited and imperfect coverage of event types, we introduce an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust the knowledge prior of event types. Experiments show our method consistently and substantially outperforms a number of baselines by at least 15 absolute F1 points under the same few-shot settings.