Resource-Enhanced Neural Model for Event Argument Extraction

TL;DR

This paper introduces a resource-enhanced neural model for event argument extraction that leverages unlabeled data, dependency syntax, and trigger-aware encoding to improve accuracy, achieving state-of-the-art results on ACE2005.

Contribution

It proposes a novel syntax-attending Transformer and trigger-aware sequence encoder to address data scarcity and long-range dependency challenges in event argument extraction.

Findings

Achieves new state-of-the-art on ACE2005 benchmark.

Effectively utilizes unlabeled data for better performance.

Improves long-range dependency modeling with syntax-guided attention.

Abstract

Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain many challenges: (1) Data scarcity. (2) Capturing the long-range dependency, specifically, the connection between an event trigger and a distant event argument. (3) Integrating event trigger information into candidate argument representation. For (1), we explore using unlabeled data in different ways. For (2), we propose to use a syntax-attending Transformer that can utilize dependency parses to guide the attention mechanism. For (3), we propose a trigger-aware sequence encoder with several types of trigger-dependent sequence representations. We also support argument extraction either from text annotated with gold entities or from plain text. Experiments on the English ACE2005 benchmark show that our approach achieves a new state-of-the-art.