Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In this paper, we propose a method with neural noise converter to alleviate the impact of noisy data, and a conditional optimal selector to make proper prediction. Our noise converter learns the structured transition matrix on logit level and captures the property of distant supervised relation extraction dataset. The conditional optimal selector on the other hand helps to make proper prediction decision of an entity pair even if the group of sentences is overwhelmed by no-relation sentences. We conduct experiments on a widely used dataset and the results show significant improvement over competitive baseline methods.
Code (0)
등록된 구현이 없습니다.
Tasks
RelationRelation ExtractionSimilar Papers 제목 키워드 기반
Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction
This paper addresses the tasks of automatic seed selection for bootstrapping relation extraction, and noise reduction for distantly supervised relation extraction. We first point out that these tasks are related. Then, i…
RelationRelation ExtractionWord Sense DisambiguationImproving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering
Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation. In distant supervision, a sentence i…
RelationRelation ExtractionSentenceAugmenting Document-level Relation Extraction with Efficient Multi-Supervision
Despite its popularity in sentence-level relation extraction, distantly supervised data is rarely utilized by existing work in document-level relation extraction due to its noisy nature and low information density. Among…
Document-level Relation ExtractionRelationRelation ExtractionSentenceA Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction
Fact triples are a common form of structured knowledge used within the biomedical domain. As the amount of unstructured scientific texts continues to grow, manual annotation of these texts for the task of relation extrac…
Knowledge Graph CompletionMultiple Instance LearningRelationRelation Classification+1Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings
Distantly-supervised relation extraction (RE) is an effective method to scale RE to large corpora but suffers from noisy labels. Existing approaches try to alleviate noise through multi-instance learning and by providing…
RelationRelation ExtractionRelationship Extraction (Distant Supervised)