A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction

TL;DR

This paper introduces TSAR, a novel two-stream AMR-enhanced model for document-level event argument extraction that effectively captures long-distance dependencies and reduces distracting context, outperforming previous methods.

Contribution

The paper presents a two-stream encoding approach combined with AMR-guided interaction and boundary loss, advancing document-level event argument extraction techniques.

Findings

TSAR achieves 2.54 F1 improvement on RAMS dataset.

TSAR achieves 5.13 F1 improvement on WikiEvents dataset.

Outperforms previous state-of-the-art methods significantly.

Abstract

Most previous studies aim at extracting events from a single sentence, while document-level event extraction still remains under-explored. In this paper, we focus on extracting event arguments from an entire document, which mainly faces two critical problems: a) the long-distance dependency between trigger and arguments over sentences; b) the distracting context towards an event in the document. To address these issues, we propose a Two-Stream Abstract meaning Representation enhanced extraction model (TSAR). TSAR encodes the document from different perspectives by a two-stream encoding module, to utilize local and global information and lower the impact of distracting context. Besides, TSAR introduces an AMR-guided interaction module to capture both intra-sentential and inter-sentential features, based on the locally and globally constructed AMR semantic graphs. An auxiliary boundary loss is introduced to enhance the boundary information for text spans explicitly. Extensive experiments illustrate that TSAR outperforms previous state-of-the-art by a large margin, with 2.54 F1 and 5.13 F1 performance gain on the public RAMS and WikiEvents datasets respectively, showing the superiority in the cross-sentence arguments extraction. We release our code in https://github.com/ PKUnlp-icler/TSAR.