Distant supervision for relation extraction with hierarchical selective attention. (December 2018)

• Record Type: Journal Article
• Authors: Zhou, Peng; Xu, Jiaming; Qi, Zhenyu; Bao, Hongyun; Chen, Zhineng; Xu, Bo
• Is Part Of: Neural networks. Volume 108(2018)
• Page Start: 240
• Page End: 247
• Publication Date: 2018-12
• Subjects: Relation extraction -- Distant supervision -- Hierarchical attention -- Piecewise convolutional neural networks; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2018.08.016
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Distant supervised relation extraction is an important task in the field of natural language processing. There are two main shortcomings for most state-of-the-art methods. One is that they take all sentences of an entity pair as input, which would result in a large computational cost. But in fact, few of most relevant sentences are enough to recognize the relation of an entity pair. To tackle these problems, we propose a novel hierarchical selective attention network for relation extraction under distant supervision. Our model first selects most relevant sentences by taking coarse sentence-level attention on all sentences of an entity pair and then employs word-level attention to construct sentence representations and fine sentence-level attention to aggregate these sentence representations. Experimental results on a widely used dataset demonstrate that our method performs significantly better than most of existing methods.