Enriched Attention for Robust Relation Extraction
The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the models do not scale well to long sentences with multiple entities and relations. In this work, we address this problem with an enriched attention mechanism. Attention allows the model to focus on parts of the input sentence that are relevant to relation extraction. We propose to enrich the attention function with features modeling knowledge about the relation arguments and the shortest dependency path between them. Thus, for different relation arguments, the model can pay attention to different parts of the sentence. Our model outperforms prior work using comparable setups on two popular benchmarks, and our analysis confirms that it indeed scales to long sentences with many entities.
Code (0)
등록된 구현이 없습니다.
Tasks
RelationRelation ExtractionSentenceSimilar Papers 제목 키워드 기반
A Feature-Enriched Tree Kernel for Relation Extraction
Joint Entity and Relation Extraction from Scientific Documents: Role of Linguistic Information and Entity Types
Scientific articles contain various types of domain-specific entities and relations between them. The entities and their relations succinctly capture important information about the topic of the document and hence, the…
ArticlesJoint Entity and Relation ExtractionJoint Entity and Relation Extraction on Scientific DataPOS+3EnriCo: Enriched Representation and Globally Constrained Inference for Entity and Relation Extraction
Joint entity and relation extraction plays a pivotal role in various applications, notably in the construction of knowledge graphs. Despite recent progress, existing approaches often fall short in two key aspects: richne…
Joint Entity and Relation ExtractionKnowledge GraphsRelationRelation ExtractionDissecting Recall of Factual Associations in Auto-Regressive Language Models
Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved…
AttributeAttribute ExtractionRelationBoosting Open Information Extraction with Noun-Based Relations
Open Information Extraction (Open IE) is a strategy for learning relations from texts, regardless the domain and without predefining these relations. Work in this area has focused mainly on verbal relations. In order to …
Open Information ExtractionRelation Extraction