中国科学院自动化研究所机构知识库

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 computationa lcost.But in fact,few of most relevant sentences are enough to recognize there lation 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 the sesentence representations.Experimental results on a widely used dataset demonstrate that our method performs significantly better than most of existing methods.