From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension

Abstract

Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels using multi-instance learning techniques. The bag-based paradigm, however, fails to leverage the inter-sentence-level and the entity-level evidence for relation extraction, and their denoising algorithms are often specialized and complicated. In this paper, we propose a new DS paradigm--document-based distant supervision, which models relation extraction as a document-based machine reading comprehension (MRC) task. By re-organizing all sentences about an entity as a document and extracting relations via querying the document with relation-specific questions, the document-based DS paradigm can simultaneously encode and exploit all sentence-level, inter-sentence-level, and entity-level evidence. Furthermore, we design a new loss function--DSLoss (distant supervision loss), which can effectively train MRC models using only $⟨$document, question, answer$⟩$ tuples, therefore noisy label problem can be inherently resolved. Experiments show that our method achieves new state-of-the-art DS performance.

12 pages, 3 figures

References in corpus (4)

• Fine-tune Bert for DocRED with Two-step Process
• Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding
• Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction
• A Practical Framework for Relation Extraction with Noisy Labels Based on Doubly Transitional Loss