Event Extraction (EE) is an essential information extraction task that aims to extract event-related information from unstructured texts. The paradigm of this task has shifted from conventional classification-based methods to more contemporary question-answering (QA)-based approaches. However, in QA-based EE, the questions' quality dramatically affects the extraction accuracy, and how to generate high-quality questions for QA-based EE still remains a challenge. In this work, to tackle this challenge, we suggest four criteria to evaluate the quality of a question and propose a reinforcement learning method for QA-Based EE that can generate fluent, generalizable, and context-dependent questions and provides clear guidance to QA models. The extensive experiments conducted on ACE and RAMS datasets have strongly validated our approach's effectiveness, which also demonstrates its robustness in scenarios with limited training data.

翻译：事件抽取（EE）是一项重要的信息抽取任务，旨在从非结构化文本中提取与事件相关的信息。该任务的范式已从传统的基于分类的方法转向更先进的基于问答（QA）的方法。然而，在基于QA的事件抽取中，问题的质量会显著影响抽取准确性，而如何为基于QA的事件抽取生成高质量问题仍是一个挑战。为应对这一挑战，本研究提出了四个评估问题质量的标准，并设计了一种基于强化学习的方法，该方法能够生成流畅、可泛化且依赖于上下文的问题，同时为QA模型提供清晰指导。在ACE和RAMS数据集上开展的大量实验充分验证了我们方法的有效性，并证明了其在训练数据有限场景下的鲁棒性。