Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (8): 1727-1741.DOI: 10.3778/j.issn.1673-9418.2111033

• Surveys and Frontiers • Previous Articles     Next Articles

Survey of Question Answering Based on Knowledge Graph Reasoning

SA Rina1, LI Yanling1, LIN Min1   

  1. 1. College of Computer Science and Technology, Inner Mongolia Normal University, Hohhot 010022, China
    2. Inner Mongolia Discipline Inspection and Supervision Big Data Laboratory, Hohhot 010015, China
  • Received:2021-11-04 Revised:2022-02-18 Online:2022-08-01 Published:2022-08-19
  • About author:SA Rina, born in 1998, M.S. candidate. Her research interests include natural language processing, spoken language understanding and know-ledge graph question answering.
    LI Yanling, born in 1978, Ph.D., professor, member of CCF. Her research interests include natural language processing, spoken language understanding, machine learning, etc.
    LIN Min, born in 1969, Ph.D., professor, member of CCF. His research interests include natural language processing, text mining, etc.
  • Supported by:
    the National Natural Science Foundation of China(61806103);the National Natural Science Foundation of China(61562068);the Project of Youth Innovation and Entrepreneurship Talents of Inner Mongolia “Grassland Talents”, the Open Project Foundation of Inner Mongolia Discipline Inspection and Supervision Big Data Laboratory(IMDBD2020013);the Science and Technology Plan Project of Inner Mongolia Autonomous Region(JH20180175);the Innovation Fund for Postgraduates of Inner Mongolia Normal University(CXJJS20127);the Scientific and Technological Research Projects of Colleges and Universities in Inner Mongolia Autonomous Region(NJZY21578);the Scientific and Technological Research Projects of Colleges and Universities in Inner Mongolia Autonomous Region(NJZY21551)

知识图谱推理问答研究综述

萨日娜1, 李艳玲1, 林民1   

  1. 1. 内蒙古师范大学 计算机科学技术学院,呼和浩特 010022
    2. 内蒙古纪检监察大数据实验室,呼和浩特 010015
  • 作者简介:萨日娜(1998—),女,内蒙古二连浩特人,硕士研究生,主要研究方向为自然语言处理、口语理解、知识图谱问答。
    李艳玲(1978—),女,内蒙古呼和浩特人,博士,教授,CCF会员,主要研究方向为自然语言处理、口语理解、机器学习等。
    林民(1969—),男,内蒙古呼和浩特人,博士,教授,CCF会员,主要研究方向为自然语言处理、文本挖掘等。
  • 基金资助:
    国家自然科学基金(61806103);国家自然科学基金(61562068);内蒙古自治区“草原英才”工程青年创新创业人才项目;内蒙古纪检监察大数据实验室开放课题基金(IMDBD2020013);内蒙古自治区科技计划项目(JH20180175);内蒙古师范大学研究生创新基金(CXJJS20127);内蒙古自治区高等学校科学技术研究项目(NJZY21578);内蒙古自治区高等学校科学技术研究项目(NJZY21551)

Abstract:

Knowledge graph question answering (KGQA) is based on analysis and understanding of questions and knowledge graph (KG) to obtain the answers. However, due to the complexity of natural language questions and the incompleteness of KG, the accuracy of answers can not be improved effectively. The knowledge graph reasoning technology can infer the missing entities in the KG and the implied relations between entities. Therefore, its application in KGQA can further improve the accuracy of answer prediction. In recent years, with the development of KGQA datasets and flexible application of knowledge graph reasoning technology, the development of the KGQA is greatly promoted. In this paper, question answering based on knowledge graph reasoning is summarized from three aspects. Firstly, this paper gives a brief overview of question answering based on knowledge graph reasoning, and introduces its challenges and related datasets. Secondly, this paper introduces the application of knowledge graph reasoning in open domain question answering, commonsense question answering and temporary knowledge question answering, and analyzes the advantages and disadvantages of each method. The open domain question answering methods are further summarized as graph embedding methods, deep learning methods and logic methods. Finally, this paper summarizes the work and prospects the future research in view of the current problems of question answering based on knowledge graph reasoning.

Key words: intelligent questions and answers, knowledge graph reasoning, knowledge graph question answering (KGQA)

摘要:

知识图谱问答(KGQA)通过对问题进行分析理解,结合知识图谱(KG)获取答案。但因自然语言问题的复杂性以及知识图谱的不完整性,答案准确率得不到有效提升。而知识图谱推理技术可以推断出知识图谱中缺失的实体以及实体间隐含的关系,因此,将知识图谱推理技术应用于知识图谱问答中可以进一步提升答案预测的准确性。近年来,知识图谱问答数据集的提出以及知识图谱推理技术的灵活应用,极大地推动了知识图谱问答的发展。对知识图谱推理问答从三方面进行归纳总结:首先对知识图谱推理问答进行了简要概述,并介绍了其面临的挑战以及相关数据集;其次对知识图谱推理在开放域问答、常识问答以及时序知识问答中的应用分别进行介绍,并分析了各问答方法的优劣,其中开放域问答方法进一步归纳为基于图嵌入的方法、基于深度学习的方法、基于逻辑的方法;最后总结工作,并根据当前知识图谱推理问答存在的问题对未来研究进行展望。

关键词: 智能问答, 知识图谱推理, 知识图谱问答(KGQA)

CLC Number: