Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction
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.
Code (1)
Tasks
Document-level Relation ExtractionRelationRelation ClassificationRelation ExtractionSentenceSimilar Papers 제목 키워드 기반
Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from uninten…
counterfactualRelationRelation ExtractionSentenceShould We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from uninten…
counterfactualRelationRelation ExtractionSentenceTowards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution
We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions …
coreference-resolutionCoreference ResolutionEntity LinkingStructured PredictionExplicitly Capturing Relations between Entity Mentions via Graph Neural Networks for Domain-specific Named Entity Recognition
Named entity recognition (NER) is well studied for the general domain, and recent systems have achieved human-level performance for identifying common entity types. However, the NER performance is still moderate for spec…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERGlobal-to-Local Neural Networks for Document-Level Relation Extraction
Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions th…
Document-level Relation ExtractionRelationRelation Extraction