面向知识库问答的实体链接方法  

An Entity Linking Approach for Knowledge Base Question Answering

作　　者：赵畅 李慧颖[1] ZHAO Chang;LI Huiying(School of Computer Science and Engineering,Southeast University,Nanjing,Jiangsu 210000,China)

机构地区：[1]东南大学计算机科学与工程学院

出　　处：《中文信息学报》2019年第11期125-133,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61502095);江苏省自然科学基金(BK20140643)

摘　　要：面向知识库问答的实体链接是指将自然语言问句中实体指称链接到知识库中实体的方法。目前主要面临两个问题:第一是自然语言问句短,实体指称上下文不充分;第二是结构化知识库中实体的文本描述信息少。因此,该文提出了分别利用候选实体的类别、关系和邻近实体作为候选实体表示的方法,弥补知识库实体描述信息不足的问题。同时,通过语料训练得到问句指称的相似实体指称作为其背景知识。最后,结合实体流行度,共同作为实体消歧的特征。实验结果表明,上述提到所有特征的线性组合在数据集上高于单个特征的结果,表现最佳。Entity linking for knowledge base question answering is to link the entity mention in the natural language question to a target entity in the knowledge base.This paper employs the candidate entity’s types,relationships and neighboring entities as the candidate entity representation,so as to solve the problem of insufficient description information of the entity in the knowledge base.At the same time,the similar entity mentions obtained by training the corpus are considered as the mention’s background knowledge.Finally,the proposed features combine the entity popularity feature to solve the entity disambiguation problem.The experimental results on the data set show that the linear combination of all the above-mentioned features is better than the single feature.

关 键 词：知识库问答 实体链接 实体消歧 Freebase 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]