Path-Based Attention Neural Model for Fine-Grained Entity Typing
원문 초록
Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need hand-labeled data, but they neglect the label noise in the automatically labeled training corpus. Although recent studies use many features to prune wrong data ahead of training, they suffer from error propagation and bring much complexity. In this paper, we propose an end-to-end typing model, called the path-based attention neural model (PAN), to learn a noise- robust performance by leveraging the hierarchical structure of types. Experiments demonstrate its effectiveness.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Refining Wikidata Taxonomy using Large Language Models
REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing
Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings
Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains
Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.