MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection

TL;DR

MsPrompt introduces a multi-step prompt learning approach with debiasing techniques for few-shot event detection, significantly improving performance in low-resource scenarios by leveraging ontology and prototypical modules.

Contribution

The paper proposes MsPrompt, a novel multi-step prompt learning framework that effectively debiases few-shot event detection by combining under-sampling, knowledge-enhanced prompts, and prototypical classification.

Findings

Outperforms state-of-the-art models on ACE-2005 and FewEvent datasets.

Achieves 11.43% higher weighted F1-score in low-resource settings.

Demonstrates strong debiasing capabilities in few-shot event detection.

Abstract

Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly. Traditional ED models are too data-hungry to accommodate real applications with scarce labeled data. Besides, typical ED models are facing the context-bypassing and disabled generalization issues caused by the trigger bias stemming from ED datasets. Therefore, we focus on the true few-shot paradigm to satisfy the low-resource scenarios. In particular, we propose a multi-step prompt learning model (MsPrompt) for debiasing few-shot event detection, that consists of the following three components: an under-sampling module targeting to construct a novel training set that accommodates the true few-shot setting, a multi-step prompt module equipped with a knowledge-enhanced ontology to leverage the event semantics and latent prior knowledge in the PLMs sufficiently for tackling the context-bypassing problem, and a prototypical module compensating for the weakness of classifying events with sparse data and boost the generalization performance. Experiments on two public datasets ACE-2005 and FewEvent show that MsPrompt can outperform the state-of-the-art models, especially in the strict low-resource scenarios reporting 11.43% improvement in terms of weighted F1-score against the best-performing baseline and achieving an outstanding debiasing performance.