Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

TL;DR

This paper introduces a novel few-shot event detection method using a dynamic-memory-based prototypical network that enhances prototype quality and robustness through multi-hop contextual learning.

Contribution

It proposes a Dynamic-Memory-Based Prototypical Network (DMB-PN) that improves event prototype learning and sentence encoding for few-shot event detection tasks.

Findings

DMB-PN outperforms baseline models in sample scarcity scenarios.

The model is more robust with a large variety of event types.

It effectively distills contextual information from event mentions.

Abstract

Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.