作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (11): 84-89. doi: 10.19678/j.issn.1000-3428.0055720

• 人工智能与模式识别 • 上一篇    下一篇

基于半边原理的知识图谱补全

程涛1, 陈恒1,2, 李冠宇1   

  1. 1. 大连海事大学 信息科学技术学院, 辽宁 大连 116026;
    2. 大连外国语大学 语言智能研究中心, 辽宁 大连 116044
  • 收稿日期:2019-08-12 修回日期:2019-11-08 发布日期:2019-11-22
  • 作者简介:程涛(1995-),男,硕士研究生,主研方向为智能信息处理;陈恒,副教授、博士研究生;李冠宇,教授、博士。
  • 基金资助:
    国家自然科学基金(61976032,61371090,61602076,61702072);国家社会科学基金(15BYY028);辽宁省自然科学基金(20170540232,20170540144,20180540003);大连外国语大学研究创新团队项目"计算语言学与人工智能创新团队"(2016CXTD06)。

Knowledge Graph Completion Based on Half-Edge Principle

CHENG Tao1, CHEN Heng1,2, LI Guanyu1   

  1. 1. Faculty of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China;
    2. Research Center for Language Intelligence, Dalian University of Foreign Languages, Dalian, Liaoning 116044, China
  • Received:2019-08-12 Revised:2019-11-08 Published:2019-11-22

摘要: 针对现有知识图谱补全算法耗时长和准确性差的问题,构建一种基于半边的多层卷积模型。通过引入半边原理,运用实体的描述信息和关系自身的特性,结合两者的语义相似度对关系所连接的头尾实体进行约束,组成半边,在此基础上使用卷积神经网络进行知识图谱补全。该模型将只含有一个实体和关系的不完全RDF三元组以半边的形式保存,便于补全扩充的知识图谱。实验结果表明,与TransE、DKRL等模型相比,该模型具有较优的实体和关系预测性能,同时能有效缩短运行时间。

关键词: 半边原理, 卷积神经网络, 知识图谱补全, 实体预测, 关系预测

Abstract: Existing knowledge graph completion algorithms are time-consuming and inaccurate.To address these problems,this paper proposes a multi-layer convolution model based on half-edge.The model introduces the half-edge principle,and uses the descriptive information of the entity and the characteristics of the relation itself to constrain the head and tail entities connected by the relation based on their semantic similarity,so as to form the half-edge.On this basis,the Convolutional Neural Network(CNN) is used to complete the knowledge graph.In this model,the incomplete RDF triples containing only one entity and relationship are saved in the form of half-edge,which facilitates the completion of extended knowledge graphs and provides a foundation for the dynamic completion of knowledge graphs.Experimental results show that the proposed model has better performance in entity prediction and relationship prediction than TransE,DKRL and other models,and can effectively reduce the running time.

Key words: half-edge principle, Convolutional Neural Network(CNN), knowledge graph completion, entity prediction, relation prediction

中图分类号: