大数据 ›› 2021, Vol. 7 ›› Issue (3): 2021025-.doi: 10.11959/j.issn.2096-0271.2021025

• 专题:基于大数据的知识图谱及其应用 • 上一篇    

知识图谱推理:现代的方法与应用

王文广   

  1. 达而观信息科技(上海)有限公司,上海 201203
  • 出版日期:2021-05-01 发布日期:2021-05-01
  • 作者简介:王文广(1984- ),男,达而观信息科技(上海)有限公司高级工程师、副总裁,中国计算机学会会员、中国中文信息学会语言与知识计算专业委员会委员、中国人工智能学会深度学习专业委员会委员,主要研究方向为知识图谱、自然语言处理、计算机视觉、深度学习、深度强化学习等。

Knowledge graph reasoning: modern methods and applications

Wenguang WANG   

  1. DataGrand Inc., Shanghai 201203, China
  • Online:2021-05-01 Published:2021-05-01

摘要:

知识图谱推理技术旨在根据已有的知识推导出新的知识,是使机器智能具有和人类一样的推理和决策能力的关键技术之一。系统地研究了知识图谱推理的现代方法,以统一的框架介绍了向量空间中进行知识图谱推理的模型,包括基于几何运算嵌入欧几里得空间和双曲空间的方法,基于卷积神经网络、胶囊网络、图神经网络等深度网络模型的方法。同时,系统地梳理了知识推理技术在各技术领域和各行业的应用情况,指出了当前存在的挑战以及其中蕴含的机会。

关键词: 知识推理, 双曲空间嵌入, 几何运算, 胶囊网络, 图神经网络

Abstract:

Knowledge reasoning over knowledge graph aims to discover new knowledge according to the existing knowledge.It is a pivotal technology to realize the human reasoning and decision-making ability of machine.The modern methods of knowledge reasoning over knowledge graph were studied systematically.And the methods based on vector representations with a unified framework were introduced, including the methods based on embedding into Euclidean space and hyperbolic space, and based on deep learning methods such as convolution neural network, capsule network, graph neural network, etc.Simultaneously, the applications of knowledge reasoning in various technical fields and industries were presented, and the existing challenges and opportunities were pointed out as well.

Key words: knowledge reasoning, hyperbolic space embedding, geometric operation, capsule network, graph neural network

中图分类号: 

No Suggested Reading articles found!