Recurrent event query decoder for document-level event extraction

Document-level event extraction is a challenging task in natural language processing, as it involves multiple events within a document and scattered event arguments across sentences. To tackle these challenges, we propose a recurrent event query decoder, i.e., a recurrent module that dynamically updates event queries to capture cross-event dependencies. Our approach then generates arguments by extracting role-argument relations using bilinear mapping, which helps address the issue of scattered arguments. Experimental results demonstrate that our proposed approach outperforms state-of-the-art models on a large-scale public dataset and actual application data, achieving significant improvements in F1-score. In domain-specific event extraction applications, our method achieves higher accuracy with fewer resources compared to general-purpose large language models. [Display omitted] •The proposed recurrent event query decoder captures cross-event dependencies.•The proposed bilinear mapping enables the extraction of role-argument relations.•Our method sets new SOTA on both a large public dataset and real-world data.•Our approach outperforms large language models fine-tuned on the same data.