大数据 ›› 2021, Vol. 7 ›› Issue (3): 60-79.doi: 10.11959/j.issn.2096-0271.2021026

• 专题:基于大数据的知识图谱及其应用 • 上一篇    下一篇

知识图谱多跳问答推理研究进展、挑战与展望

杜会芳1, 王昊奋1, 史英慧2, 王萌3   

  1. 1 同济大学设计创意学院,上海 200092
    2 东南大学网络空间与安全学院,江苏 无锡 214100
    3 东南大学计算机科学与工程学院,江苏 南京 211189
  • 出版日期:2021-05-15 发布日期:2021-05-01
  • 作者简介:杜会芳(1991- ),女,同济大学设计创意学院博士生,主要研究方向为知识图谱、智能问答。
    王昊奋(1982- ),男,同济大学设计创意学院特聘研究员,中国计算机学会(CCF)理事、计算机术语审定委员会副主任、CCF TF SIGKG主席,OpenKG联合创始人,主要研究方向为知识图谱、自然语言处理、问答对话、智能内容生成。
    史英慧(1998- ),女,东南大学网络空间与安全学院硕士生,主要研究方向为知识图谱、多模态数据。
    王萌(1989- ),男,博士,东南大学计算机科学与工程学院讲师,CCF会员,东南大学“至善青年学者”支持计划获得者,主要研究方向为知识图谱、多模态数据、自然语言处理。
  • 基金资助:
    中央高校基本科研业务专项资金资助项目(22120210109)

Progress, challenges and research trends of reasoning in multi-hop knowledge graph based question answering

Huifang DU1, Haofen WANG1, Yinghui SHI2, Meng WANG3   

  1. 1 College of Design and Innovation, Tongji University, Shanghai 200092, China
    2 School of Cyber Science and Engineering, Southeast University, Wuxi 214100, China
    3 School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
  • Online:2021-05-15 Published:2021-05-01
  • Supported by:
    Fundamental Research Funds for the Central Universities(22120210109)

摘要:

近年来,知识图谱问答在医疗、金融、政务等领域被广泛应用。用户不再满足于关于实体属性的单跳问答,而是更多地倾向表达复杂的多跳问答需求。为了应对上述复杂多跳问答,各种不同类型的推理方法被陆续提出。系统地介绍了基于嵌入、路径、逻辑的多跳知识问答推理的最新研究进展以及相关数据集和评测指标,并重点围绕前沿问题进行了讨论。最后总结了现有方法的不足,并展望了未来的研究方向。

关键词: 知识图谱, 多跳问答, 推理

Abstract:

Recently, knowledge graph based question answering has been widely used in many fields such as medical care, finance, and government affairs.Users are no longer satisfied with question answering service of single-hop entity attributes, but want service which can handle complex multi-hop question.In order to accurately and deeply understand multi-hop questions, various types of reasoning methods have been proposed.The latest research methods of multi-hop knowledge graph based question answering were systematically introduced, as well as related datasets and evaluation metrics.These

Key words: knowledge graph, multi-hop question answering, reasoning

中图分类号: 

No Suggested Reading articles found!