Sentence-level Event Detection without Triggers via Prompt Learning and Machine Reading Comprehension

TL;DR

This paper introduces a trigger-free sentence-level event detection method that leverages prompt learning and machine reading comprehension, reducing reliance on annotated trigger words while maintaining competitive accuracy.

Contribution

It proposes a novel trigger-free event detection model using prompt learning and MRC, addressing annotation challenges and improving flexibility over traditional methods.

Findings

Achieves competitive performance on ACE2005 and MAVEN datasets.

Reduces dependency on annotated trigger words.

Demonstrates effectiveness of prompt learning in event detection.

Abstract

The traditional way of sentence-level event detection involves two important subtasks: trigger identification and trigger classifications, where the identified event trigger words are used to classify event types from sentences. However, trigger classification highly depends on abundant annotated trigger words and the accuracy of trigger identification. In a real scenario, annotating trigger words is time-consuming and laborious. For this reason, we propose a trigger-free event detection model, which transforms event detection into a two-tower model based on machine reading comprehension and prompt learning. Compared to existing trigger-based and trigger-free methods, experimental studies on two event detection benchmark datasets (ACE2005 and MAVEN) have shown that the proposed approach can achieve competitive performance.