? 基于注意力机制的树状神经网络知识库问答模型
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (4) :805-813    DOI: 10.1007/s11390-017-1761-8
Special Issue on Deep Learning << Previous Articles | Next Articles >>
基于注意力机制的树状神经网络知识库问答模型
Jun Yin1, Wayne Xin Zhao2,3, Member, CCF, Xiao-Ming Li1,*, Fellow, CCF
1 School of Electronic Engineering and Computer Science, Peking University, Beijing 100871, China;
2 School of Information, Renmin University of China, Beijing 100872, China;
3 Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou 510006, China
Type-Aware Question Answering over Knowledge Base with Attention-Based Tree-Structured Neural Networks
Jun Yin1, Wayne Xin Zhao2,3, Member, CCF, Xiao-Ming Li1,*, Fellow, CCF
1 School of Electronic Engineering and Computer Science, Peking University, Beijing 100871, China;
2 School of Information, Renmin University of China, Beijing 100872, China;
3 Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou 510006, China

摘要
参考文献
相关文章
Download: [PDF 683KB]  
摘要 基于知识库的问答旨在对输入的自然语言问题从知识库找出结构化的答案。该任务的关键步骤是如何表示和理解自然语言问题。本文我们提出使用树状神经网络基于语法构造数对自然语言问题建模。我们发现自然语言问题语法构造树中的不同成分具有自己的语义特征,对应解决知识库问答系统中不同的子任务。基于这点发现,我们将实体类型信息考虑进来作为辅助监督信号,提升知识库问答系统效果。我们提出的方法叫实体类型感知的问答系统(type-aware QA)。基于注意力机制,我们在一个统一的神经网络模型中同时刻画答案实体和实体类型。对于问题表示,我们联合不同语法构造树组件表示和面向不同子任务的注意力权重,而不是简单使用语法构造树根节点表示。公开数据集上的实验结果表明我们提出的模型对知识库问答效果有提升。更具体的,学习到的注意力权重对于理解问题意义重大,过程中产生的中间节点表示可用于分析其在问答系统中的不同子任务的作用和效果。
关键词问答系统   深度神经网络   知识库     
Abstract: Question answering (QA) over knowledge base (KB) aims to provide a structured answer from a knowledge base to a natural language question. In this task, a key step is how to represent and understand the natural language query. In this paper, we propose to use tree-structured neural networks constructed based on the constituency tree to model natural language queries. We identify an interesting observation in the constituency tree:different constituents have their own semantic characteristics and might be suitable to solve different subtasks in a QA system. Based on this point, we incorporate the type information as an auxiliary supervision signal to improve the QA performance. We call our approach type-aware QA. We jointly characterize both the answer and its answer type in a unified neural network model with the attention mechanism. Instead of simply using the root representation, we represent the query by combining the representations of different constituents using task-specific attention weights. Extensive experiments on public datasets have demonstrated the effectiveness of our proposed model. More specially, the learned attention weights are quite useful in understanding the query. The produced representations for intermediate nodes can be used for analyzing the effectiveness of components in a QA system.
Keywordsquestion answering   deep neural network   knowledge base     
Received 2016-12-20;
本文基金:

This work has been partially supported by the National Basic Research 973 Program of China under Grant No. 2014CB340405 and the National Natural Science Foundation of China under Grant No. U1536201. Wayne Xin Zhao was partially supported by Beijing Natural Science Foundation under Grant No. 4162032, and the Opening Project of Guangdong Province Key Laboratory of Big Data Analysis and Processing under Grant No. 2017001.

通讯作者: Xiao-Ming Li     Email: lxm@pku.edu.cn
About author: Jun Yin received her B.S. degree in computer science and technology from Sichuan University, Chengdu, in 2011. She is now a Ph.D. candidate in the School of Electronic Engineering and Computer Science, Peking University, Beijing. Her research interests include deep learning, question answering, natural language generation, and knowledge management.
引用本文:   
Jun Yin, Wayne Xin Zhao, Xiao-Ming Li.基于注意力机制的树状神经网络知识库问答模型[J]  Journal of Computer Science and Technology , 2017,V32(4): 805-813
Jun Yin, Wayne Xin Zhao, Xiao-Ming Li.Type-Aware Question Answering over Knowledge Base with Attention-Based Tree-Structured Neural Networks[J]  Journal of Computer Science and Technology, 2017,V32(4): 805-813
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1761-8
Copyright 2010 by Journal of Computer Science and Technology