基于实体排序和联合事实选择的知识库问答  

Simple question answering with entity ranking and joint fact selection

作　　者：刘月峰[1] 张丽娜 杨宇慧 张公 张晨荣 Liu Yuefeng;Zhang Lina;Yang Yuhui;Zhang Gong;Zhang Chenrong(School of Information Engineering,Inner Mongolia University of Science&Technology,Baotou Inner Mongolia 014010,China)

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《计算机应用研究》2020年第11期3321-3325,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(51565046);内蒙古自然科学基金资助项目(2018MS06019)。

摘　　要：针对大多数简单知识库问答模型没有充分利用候选实体排序,并且往往忽略实体和关系之间依赖的问题,提出了基于实体排序和联合事实选择的方法。整个过程分为模式抽取、实体排序和联合事实选择三个步骤。首先,通过BILSTM-CRF算法对自然语言问题进行模式提取,将其划分为实体提及(mention)和问题模式(pattern)两部分;然后,同时利用subject(主题实体)和mention的字面和语义相似性对候选实体进行排序,抽取相关事实;最后,为了能在候选事实池中选择出最正确的实体—关系对,联合事实选择模型利用多级别编码增强整个过程。实验证明,该方法在simple questions dataset的准确率、召回率都有明显的提升。实验结果表明所提方法在知识库的简单问答上具有可行性。To solve the problem that most models do not make full use of candidate entity ranking and ignore the subject-relation dependency in simple question answering over knowledge graph,this paper proposed a method based on entity ranking and joint fact selection.It divided the whole process into three steps:pattern extraction,entity ranking and joint fact selection.Firstly,it extracted the natural language question by the BILSTM-CRF,divided it into two parts:mention and pattern.Then,it sorted the candidate entities by using the literal and semantic similarity of the subject and the mention to select candidate facts.Finally,in order to select the most correct subject-relation in the candidate fact pool,the joint fact selection model enhanced this process with multi-level encoding.Experiments show that the method can significantly improve the accuracy,recall rate on the simple questions dataset.The experimental results indicate the feasibility of the proposed method for simple question answering over knowledge graph.

关 键 词：知识库问答 深度学习 相似度计算 联合事实选择 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]