Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (9): 30-50.DOI: 10.3778/j.issn.1002-8331.2111-0248

• Research Hotspots and Reviews • Previous Articles     Next Articles

Comprehensive Survey on Knowledge Graph Embedding

XU Youwei, ZHANG Hongjun, CHENG Kai, LIAO Xianglin, ZHANG Zixuan, LI Lei   

  1. Institute of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, China
  • Online:2022-05-01 Published:2022-05-01

知识图谱嵌入研究综述

徐有为,张宏军,程恺,廖湘琳,张紫萱,李雷   

  1. 陆军工程大学 指挥控制工程学院,南京 210007

Abstract: With the rapid development of Internet technology and application mode, knowledge graph has received much attention due to its rich and intuitive expressivity, and a large number of researches in knowledge representation learning have been accumulated, playing an important role in vertical searching, intelligent question answering and other application fields. On the basis of summarizing the existing research on knowledge graph embedding, knowledge graph embedding models are divided into two categories based on the number of knowledge graphs: link prediction models oriented to a single knowledge graph and entity alignment models oriented to multiple knowledge graphs. The standard processing flow of knowledge graph embedding models are also analyzed by categories. Detail information are combed according to model assumptions, implementation methods, semantic-capturing levels and other aspects. By fully discussing on the existed problems of knowledge graph embedding models, future research directions of knowledge graph embedding are prospected.

Key words: knowledge graph, knowledge representation learning, link prediction, entity alignment

摘要: 随着互联网技术和应用模式的迅猛发展,表达方式丰富直观的知识图谱得到了大量关注,在知识表示学习方面积累了丰富研究成果,这些研究已在垂直搜索、智能问答等应用领域发挥了重要作用。在总结现有知识图谱嵌入研究基础之上,以面向的知识图谱数量为依据,将知识图谱嵌入模型分为面向单个知识图谱的链接预测模型和面向多个知识图谱的实体对齐模型两大类;逐类分析了知识图谱嵌入模型的标准处理流程,并在模型假设、实现方法、语义捕获层次等方面做了详细对比;通过充分探讨现有知识图谱嵌入模型存在的问题,展望了知识图谱嵌入的未来研究方向。

关键词: 知识图谱, 知识表示学习, 链接预测, 实体对齐