EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction
This work addresses inconsistency issues for downstream applications like knowledge base population and question answering, representing an incremental improvement over existing methods.
The paper tackles inconsistency in document-level event argument extraction by proposing that participants maintain consistent roles across multiple events, and introduces the EA^2E model with augmented context to enforce event-event relation constraints, achieving improved performance on WIKIEVENTS and ACE2005 datasets.
Events are inter-related in documents. Motivated by the one-sense-per-discourse theory, we hypothesize that a participant tends to play consistent roles across multiple events in the same document. However recent work on document-level event argument extraction models each individual event in isolation and therefore causes inconsistency among extracted arguments across events, which will further cause discrepancy for downstream applications such as event knowledge base population, question answering, and hypothesis generation. In this work, we formulate event argument consistency as the constraints from event-event relations under the document-level setting. To improve consistency we introduce the Event-Aware Argument Extraction (EA$^2$E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$^2$E compared to baseline methods.