RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

TL;DR

This paper introduces RAAT, a relation-augmented transformer that models argument relations to improve document-level event extraction, effectively addressing cross-sentence and multi-event challenges with state-of-the-art results.

Contribution

The paper proposes RAAT, a novel transformer architecture that captures multi-scale argument relations and employs multi-task learning for enhanced event extraction performance.

Findings

Achieves state-of-the-art results on two public datasets.

Effectively models cross-sentence argument relations.

Improves event extraction accuracy with relation-aware attention.

Abstract

In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multiple events may lie in one document (multi-event issue). In this paper, we argue that the relation information of event arguments is of great significance for addressing the above two issues, and propose a new DEE framework which can model the relation dependencies, called Relation-augmented Document-level Event Extraction (ReDEE). More specifically, this framework features a novel and tailored transformer, named as Relation-augmented Attention Transformer (RAAT). RAAT is scalable to capture multi-scale and multi-amount argument relations. To further leverage relation information, we introduce a separate event relation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance. Extensive experiments demonstrate the effectiveness of the proposed method, which can achieve state-of-the-art performance on two public datasets. Our code is available at https://github. com/TencentYoutuResearch/RAAT.