EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction

TL;DR

This paper introduces EA$^2$E, a model that enhances consistency in document-level event argument extraction by leveraging event-event relations, improving accuracy over baseline methods.

Contribution

The paper proposes a novel event-aware model that incorporates event relations to improve argument extraction consistency across documents.

Findings

EA$^2$E outperforms baseline models on WIKIEVENTS and ACE2005 datasets.

Event-aware constraints improve argument extraction consistency.

Enhanced context modeling leads to better downstream application performance.

Abstract

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.