Continual Few-shot Event Detection via Hierarchical Augmentation Networks

TL;DR

This paper introduces Hierarchical Augmentation Networks (HANet), a novel memory-based framework for continual few-shot event detection that effectively memorizes previous event types and learns new ones with limited data, outperforming existing methods.

Contribution

The paper proposes HANet, which combines prototypical and contrastive augmentation modules to improve continual few-shot event detection, addressing data scarcity and memory challenges.

Findings

HANet significantly outperforms previous state-of-the-art methods.

The model effectively memorizes previous event types with limited memory.

HANet demonstrates superior performance compared to ChatGPT in experiments.

Abstract

Traditional continual event detection relies on abundant labeled data for training, which is often impractical to obtain in real-world applications. In this paper, we introduce continual few-shot event detection (CFED), a more commonly encountered scenario when a substantial number of labeled samples are not accessible. The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples. To mitigate these challenges, we propose a memory-based framework: Hierarchical Augmentation Networks (HANet). To memorize previous event types with limited memory, we incorporate prototypical augmentation into the memory set. For the issue of learning new event types in few-shot scenarios, we propose a contrastive augmentation module for token representations. Despite comparing with previous state-of-the-art methods, we also conduct comparisons with ChatGPT. Experiment results demonstrate that our method significantly outperforms all of these methods in multiple continual few-shot event detection tasks.