Exploiting Explicit Matching Knowledge with Long Short-Term Memory

摘要：

　　Recently neural network models are widely applied in text-matchingtasks like community-based question answering(cQA).The strong generaliza-tion power of neural networks enables these methods to find texts with similar topics but miss detailed matching information.However,as proven by traditional methods,the explicit lexical matching knowledge is important for effective an-swer retrieval.In this paper,we propose an ExMaLSTM model to incorporate the explicit matching knowledgeinto the long short-term memory(LSTM)neural network.We extract explicit lexical matching features with prior knowledge and then add themtothe local representations of questions.We summarize the overall matching status by using a bi-directional LSTM.The final relevance score is cal-culated using a gate network,which can dynamically assign appropriate weights to the explicit matching score and the implicit relevance score.We conduct ex-tensive experiments for answer retrieval in a cQA dataset.The results show that our proposed ExMaLSTM model outperforms both the traditional methods and various state-of-the-art neural network models significantly.

关键词： lexical matching knowledge LSTM question answering

作者: Xinqi Bao Yunfang Wu

作者单位: Key Laboratory of Computational Linguistics(Peking University),Ministry of Education School of Electronic Engineering and Computer Science,Peking University

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）