知识图谱在实体检索中的应用研究综述  

A Review of the Application of Knowledge Graph in Entity Retrieval

作　　者：阮光册 樊宇航 夏磊[2] Ruan Guangce;Fan Yuhang;Xia Lei(Department of Information Management,Faculty of Economics and Management,East China Normal University,Shanghai 200241;Shanghai Library,Shanghai 200031)

机构地区：[1]华东师范大学经济与管理学部信息管理系,上海200241 [2]上海图书馆会展中心,上海200031

出　　处：《图书情报工作》2020年第14期126-135,共10页Library and Information Service

基　　金：上海市软科学研究计划项目"数据智能时代基于深度学习的情报处理分析研究"(项目编号:19692106600)研究成果之一。

摘　　要：[目的/意义]梳理基于知识图谱的实体检索的研究脉络和重点,探索未来该领域的发展方向。[方法/过程]概述基于知识图谱的实体检索的形式化定义、实现路径以及主要的数据源;根据检索任务,将实体检索划分为匹配检索、扩展检索和推荐检索3种实现场景,并对其实现方法进行综述。[结果/结论]随着应用的不断深入,基于知识图谱的实体检索研究开始关注如何优化用户的检索体验和提供多样性的检索结果,未来将在检索结果可解释性、跨领域知识图谱检索等多个方面展开深入的研究。[Purpose/significance]To sort out the research context and key points of entity retrieval based on knowledge graph,and explore the future development direction of this field.[Method/process]This paper firstly gave the formal definition,the implementation path and main data sources of entity retrieval on knowledge graph.Then,according to the retrieval task,the application of entity retrieval was divided into match retrieval,extended retrieval and recommended recommendation,and the implementation methods were summarized.[Result/conclusion]With the development of the application,the research of entity retrieval based on knowledge graph began to focus on how to improve the user's retrieval experience and provide a variety of retrieval results.The future research will be carried out on the interpretability of retrieval results,cross domain knowledge graph retrieval and so on.

关 键 词：实体检索 知识图谱 信息检索 

分 类 号：G250[文化科学—图书馆学]