Hyperspherical Dynamic Multi-Prototype with Arguments Dependencies and Role Consistency for Event Argument Extraction

ACL ARR 2025 February Submission6791 Authors

Abstract: Event Argument Extraction (EAE) aims to identify arguments and assign them to predefined roles within a document. Existing methods face challenges in modeling intra-class variance and inter-class ambiguity, hindering accurate role assignment. Inspired by how humans dynamically adjust classification criteria while maintaining category consistency (e.g., distinguishing “victim” and “attacker” roles based on contextual relationships), We propose HDMAR (Hyperspherical Dynamic Multi-Prototype with Arguments Dependencies and Role Consistency), where three innovations tackle these challenges: (1) Hyperspherical dynamic multi-prototype learning is used to capture intra-role diversity and enforce inter-role separation via hyperspherical optimization and optimal transport, (2) cross-event role consistency is used to align role representations across events, and (3) an arguments dependencies-guided encoding module enhances contextual understanding of intra-event and inter-event dependencies. Experiments on RAMS and WikiEvents demonstrate gains in accuracy, with further analysis validating the contributions of each module.

Paper Type: Long

Research Area: Information Extraction

Research Area Keywords: Event Argument Extraction

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 6791