Structured Minimally Supervised Learning for Neural Relation Extraction
We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level supervision from a KB. By explicitly reasoning about missing data during learning, our approach enables large-scale training of 1D convolutional neural networks while mitigating the issue of label noise inherent in distant supervision. Our approach achieves state-of-the-art results on minimally supervised sentential relation extraction, outperforming a number of baselines, including a competitive approach that uses the attention layer of a purely neural model.
Code (1)
Tasks
RelationRelation ExtractionSentenceSimilar Papers 제목 키워드 기반
Annotating Opinions in German Political News
This paper presents an approach to construction of an annotated corpus for German political news for the opinion mining task. The annotated corpus has been applied to learn relation extraction rules for extraction of opi…
BIG-bench Machine LearningOpinion MiningQuestion AnsweringRelation Extraction+2Minimally Supervised Method for Multilingual Paraphrase Extraction from Definition Sentences on the Web
Bootstrapping Distantly Supervised IE using Joint Learning and Small Well-structured Corpora
We propose a framework to improve performance of distantly-supervised relation extraction, by jointly learning to solve two related tasks: concept-instance extraction and relation extraction. We combine this with a novel…
RelationRelation ExtractionBootstrapping Ternary Relation Extractors
Binary relation extraction methods have been widely studied in recent years. However, few methods have been developed for higher n-ary relation extraction. One limiting factor is the effort required to generate training …
Binary Relation ExtractionRelationRelation ExtractionTripletTAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation
Direct Preference Optimization (DPO) is an effective and widely adopted approach for offline alignment but is poorly matched to ontology-driven structured prediction, where preferred and rejected JSON objects often diffe…
Information ExtractionStructured Prediction