Doc2Event: Extracting Chinese Document-Level Events into Generation Models

Current methodologies for document-level event extraction, particularly within Chinese textual data, face significant challenges, such as the extraction of isolated events and the imprecise delineation of event interrelationships. The advent of large language models, fortunately, offers a promising frontier for enhancing event extraction capabilities. In light of this, this study proposes an innovative framework for the extraction of multiple events that effectively mitigates these limitations. The proposed framework employs the Entity-based Directed Acyclic Graph(EDAG) to accurately model and articulate serialization relationships among events in Chinese documents. Furthermore, it incorporates prefix prompt, thereby broadening the applicability of generative models to document-level multi-event extraction tasks. Empirical evaluations of the proposed framework were conducted using the mT5 model on challenging datasets, including the DuEE-Fin dataset from the financial domain and the FNDEE dataset from the military domain.