AssocKD: An Association-Aware Knowledge Distillation Method for Document-Level Event Argument Extraction

• Published in: Mathematics (Basel) Vol. 12; no. 18; p. 2901
• Main Authors: Tan, Lijun, Hu, Yanli, Cao, Jianwei, Tan, Zhen
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-09-2024
• Subjects: association-aware construction; document-level event argument extraction; Documents; Electronic data processing; Innovations; Knowledge; knowledge distillation; Knowledge management; Methods; multi-event argument extraction; Statistical analysis; Teachers; Tsarnaev, Dzhokhar; China
• ISSN: 2227-7390; 2227-7390
• DOI: 10.3390/math12182901

Event argument extraction is a crucial subtask of event extraction, which aims at extracting arguments that correspond to argument roles when given event types. The majority of current document-level event argument extraction works focus on extracting information for only one event at a time without considering the association among events; this is known as document-level single-event extraction. However, the interrelationship among arguments can yield mutual gains in their extraction. Therefore, in this paper, we propose AssocKD, an Association-aware Knowledge Distillation Method for Document-level Event Argument Extraction, which enables the enhancement of document-level multi-event extraction with event association knowledge. Firstly, we introduce an association-aware training task to extract unknown arguments with the given privileged knowledge of relevant arguments, obtaining an association-aware model that can construct both intra-event and inter-event relationships. Secondly, we adopt multi-teacher knowledge distillation to transfer such event association knowledge from the association-aware teacher models to the event argument extraction student model. Our proposed method, AssocKD, is capable of explicitly modeling and efficiently leveraging event association to enhance the extraction of multi-event arguments at the document level. We conduct experiments on RAMS and WIKIEVENTS datasets and observe a significant improvement, thus demonstrating the effectiveness of our method.