Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and empirically analyze fixed discrete token template performance. As generating human-annotated question templates is often time-consuming and labor-intensive, we further propose a novel approach called "Learning to Ask," which can learn optimized question templates for EAE without human annotations. Experiments using the ACE-2005 dataset demonstrate that our method based on optimized questions achieves state-of-the-art performance in both the few-shot and supervised settings.
@article{arxiv.2110.00479,
title = {Learning to Ask for Data-Efficient Event Argument Extraction},
author = {Hongbin Ye and Ningyu Zhang and Zhen Bi and Shumin Deng and Chuanqi Tan and Hui Chen and Fei Huang and Huajun Chen},
journal= {arXiv preprint arXiv:2110.00479},
year = {2023}
}