Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction

TL;DR

This paper introduces RSMAN, a relation-specific attention mechanism that selectively emphasizes entity mentions to improve document-level relation extraction, especially when entities have multiple mentions, leading to state-of-the-art results.

Contribution

The paper proposes a novel relation-specific attention model that distinguishes mention-level features for better entity representation in document-level relation extraction.

Findings

RSMAN significantly improves relation extraction performance.

The method achieves state-of-the-art results on benchmark datasets.

Selective mention attention benefits entities with multiple mentions.

Abstract

Compared with traditional sentence-level relation extraction, document-level relation extraction is a more challenging task where an entity in a document may be mentioned multiple times and associated with multiple relations. However, most methods of document-level relation extraction do not distinguish between mention-level features and entity-level features, and just apply simple pooling operation for aggregating mention-level features into entity-level features. As a result, the distinct semantics between the different mentions of an entity are overlooked. To address this problem, we propose RSMAN in this paper which performs selective attentions over different entity mentions with respect to candidate relations. In this manner, the flexible and relation-specific representations of entities are obtained which indeed benefit relation classification. Our extensive experiments upon two benchmark datasets show that our RSMAN can bring significant improvements for some backbone models to achieve state-of-the-art performance, especially when an entity have multiple mentions in the document.