We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental results demonstrate that a well-defined and comprehensive event type prompt can significantly improve the performance of event detection, especially when the annotated data is scarce (few-shot event detection) or not available (zero-shot event detection). By leveraging the semantics of event types, our unified framework shows up to 24.3\% F-score gain over the previous state-of-the-art baselines.
@article{arxiv.2204.07241,
title = {The Art of Prompting: Event Detection based on Type Specific Prompts},
author = {Sijia Wang and Mo Yu and Lifu Huang},
journal= {arXiv preprint arXiv:2204.07241},
year = {2022}
}