95% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Natural Language Processing
Volume 8 - 2025 | doi: 10.3389/frai.2025.1520290
Enhancing Pre-trained Language Model by Answering Natural Questions for Event Extraction
Provisionally accepted- Zhejiang Chinese Medical University, Hangzhou, China
Event extraction, the task of identifying and extracting structured information about events from unstructured text. However, event extraction remains challenging due to the complexity and diversity of event expressions, as well as the ambiguity and context-dependency of language. In this paper, we propose a novel approach to enhancing event extraction by incorporating topic words and leveraging the power of answering almost natural questions. Our method formulates event extraction as a question answering task, where we construct informative questions tailored to specific event types and their associated arguments. By incorporating topic words related to the event and its context, we guide the model to focus on relevant information and filter out noise, thereby improving the precision and recall of event extraction. Our results suggest that leveraging topic words and question answering techniques can effectively address the challenges of event extraction and pave the way for more accurate and robust event extraction systems.
Keywords: Event extraction, Pre-trained language model, Topic Words, question answering, contextual information
Received: 01 Nov 2024; Accepted: 04 Apr 2025.
Copyright: © 2025 Zhang and Han. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Qing Han, Zhejiang Chinese Medical University, Hangzhou, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.