Utilizing Contextual Clues and Role Correlations for Enhancing Document-level Event Argument Extraction

TL;DR

This paper introduces CARLG, a novel framework that enhances document-level event argument extraction by integrating broader contextual clues and capturing semantic role correlations, leading to improved performance and efficiency.

Contribution

The paper proposes CARLG, a framework with two modules, CCA and RLIG, that significantly improves event argument extraction by better utilizing context and role correlations with minimal additional parameters.

Findings

Significant performance improvements on RAMS, WikiEvents, and MLEE datasets.

CARLG achieves superior inference speed compared to benchmarks.

Modules effectively capture context and role correlations.

Abstract

Document-level event argument extraction is a crucial yet challenging task within the field of information extraction. Current mainstream approaches primarily focus on the information interaction between event triggers and their arguments, facing two limitations: insufficient context interaction and the ignorance of event correlations. Here, we introduce a novel framework named CARLG (Contextual Aggregation of clues and Role-based Latent Guidance), comprising two innovative components: the Contextual Clues Aggregation (CCA) and the Role-based Latent Information Guidance (RLIG). The CCA module leverages the attention weights derived from a pre-trained encoder to adaptively assimilates broader contextual information, while the RLIG module aims to capture the semantic correlations among event roles. We then instantiate the CARLG framework into two variants based on two types of current mainstream EAE approaches. Notably, our CARLG framework introduces less than 1% new parameters yet significantly improving the performance. Comprehensive experiments across the RAMS, WikiEvents, and MLEE datasets confirm the superiority of CARLG, showing significant superiority in terms of both performance and inference speed compared to major benchmarks. Further analyses demonstrate the effectiveness of the proposed modules.