Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction
This work addresses the problem of accurately extracting relations from documents for natural language processing applications, representing an incremental advance by enhancing existing models with attention mechanisms.
The paper tackles the challenge of document-level relation extraction where entities have multiple mentions, by proposing RSMAN, a method that uses relation-specific attentions over entity mentions to improve entity representations, achieving state-of-the-art performance on benchmark datasets with significant improvements, especially for entities with multiple mentions.
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.