Distant Supervision for Relation Extraction with Neural Instance Selector

摘要：

　　Distant supervised relation extraction is an efficient method to find novel relational facts from very large corpora without expensive manual annotation.However,distant supervision will inevitably lead to wrong label problem,and these noisy labels will substantially hurt the performance of relation extraction.Existing methods usually use multi-instance learning and selective attention to reduce the influence of noise.However,they usually cannot fully utilize the supervision information and eliminate the effect of noise.In this paper,we propose a method called Neural Instance Selector(NIS)to solve these problems.Our approach contains three modules,a sentence encoder to encode input texts into hidden vector representations,an NIS module to filter the less informative sentences via multilayer perceptrons and logistic classification,and a selective attention module to select the important sentences.Experimental results show that our method can effectively filter noisy data and achieve better performance than several baseline methods.

关键词： Relation extraction Distant supervision Neural Instance Selector

作者: Yubo Chen Hongtao Liu Chuhan Wu Zhigang Yuan Minyu Jiang Yongfeng Huang

作者单位: Next Generation Network Lab,Department of Electronic Engineering,Tsinghua University,Beijing,China Tianjin Key Laboratory of Advanced Networking,School of Computer Science and Technology,Tianjin Univ Fan Gongxiu Honor College,Beijing University of Technology,Beijing,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 209-220

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）