Bi-directional Gated Memory Networks for Answer Selection

摘要：

　　Answer selection is a crucial subtask of the open domain question answering problem.In this paper,we introduce the Bi-directional Gated Memory Network(BGMN)to model the interactions between question and answer.We match question(P)and answer(Q)in two di-rections.In each direction(for example P →Q),sentence representation of P triggers an iterative attention process that aggregates informative evidence of Q.In each iteration,sentence representation of P and ag-gregated evidence of Q so far are passed through a gate determining the importance of the two when attend to every step of Q.Finally based on the aggregated evidence,the decision is made through a fully con-nected network.Experimental results on SemEval-2015 Task 3 dataset demonstrate that our proposed method substantially outperforms sev-eral strong baselines.Further experiments show that our model is general and can be applied to other sentence-pair modeling tasks.

关键词： Question Answering Attention Mechanism Memory Net-works

作者: Wei Wu Houfeng Wang Sujian Li

作者单位: Key Laboratory of Computational Linguistics,Ministry of Education School of Electronics Engineering and Computer Science,Peking University No.5 Yiheyuan Road,Haidian District,Beijing,100871,China

会议类型: 国内会议

会议名称: 第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

会议地点: 南京

会议语种:英文

页码: 1-12

在线出版日期: 2017-10-13（万方平台首次上网日期，不代表论文的发表时间）