一种改进的基于TransE知识图谱表示方法

doi:10.19678/j.issn.1000-3428.0054196

摘要/Abstract

摘要： 传统基于翻译模型的知识图谱表示方法难以处理一对多、多对一和多对多等复杂关系，而且通常独立地学习三元组而忽略了知识图谱的网络结构和语义信息。为解决该问题，构建一种基于TransE的TransGraph模型，该模型同时学习三元组和知识图谱网络结构特征，以有效增强知识图谱的表示效果。在此基础上，提出一种向量共享的交叉训练机制，从而实现网络结构信息和三元组信息的深度融合。在公开数据集上的实验结果表明，相比TransE模型，TransGraph模型在链路预测和三元组分类2个任务中的HITS@10、准确率指标均得到显著提升。

关键词: 知识图谱, 表示学习, TransE模型, 链路预测, 神经网络

Abstract: It is difficult for traditional representation methods based on translation models for knowledge graph to deal with complex relationships such as one to many,many to one and many to many relations.Also,they usually neglect the network structure and semantic information of knowledge graph when studying triples.To solve these problems,this paper proposes a TransGraph model based on TransE.The model learns triples and the network structure features of knowledge graph at the same time,so as to enhance the representation performance of knowledge graph.On this basis,a cross training mechanism of vector sharing is proposed in order to realize the deep fusion of network structure information and triple information.Experimental results on open datasets show that the HITS@10 and accuracy of TransGraph are significantly improved in link prediction and triple classification compared with the TransE model.

Key words: knowledge graph, representation learning, TransE model, link prediction, neural network

中图分类号:

TP391

陈文杰, 文奕, 张鑫, 杨宁, 赵爽. 一种改进的基于TransE知识图谱表示方法[J]. 计算机工程, 2020, 46(5): 63-69,77.

CHEN Wenjie, WEN Yi, ZHANG Xin, YANG Ning, ZHAO Shuang. An Improved TransE-Based Method for Knowledge Graph Representation[J]. Computer Engineering, 2020, 46(5): 63-69,77.

http://www.ecice06.com/CN/Y2020/V46/I5/63

图/表 10

20200513200849

20200513200854

20200513200858

20200513200902

20200513200907

20200513200910

20200513200915

20200513200922

20200513200926

20200513200930

参考文献

[1] LIU Zhiyuan,SUN Maosong,LIN Yankai,et al.Know-ledge representation learning:a review[J].Journal of Computer Research and Development,2016,53(2):247-261.(in Chinese)刘知远,孙茂松,林衍凯,等.知识表示学习研究进展[J].计算机研究与发展,2016,53(2):247-261.
[2] PEROZZI B,AI-RFOU R,SKIENA S.Deepwalk:online learning of social representation[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2014:701-710.
[3] FANG Yang,ZHAO Xiang,TAN Zhen,et al.A revised translation-based method for knowledge graph representation[J].Journal of Computer Research and Development,2018,55(1):139-150.(in Chinese)方阳,赵翔,谭真,等.一种改进的基于翻译的知识图谱表示方法[J].计算机研究与发展,2018,55(1):139-150.
[4] SINGHAL A.Introducing the knowledge graph:things,not things[EB/OL].[2019-02-10].http://googleblog.blogspot.co.uk./2012/05/introducing-knowledge-graph-things-not.html.
[5] CHANG Liang,ZHU Manli,GU Tianlong,et al.Knowledge graph embedding by dynamic translation[J].IEEE Acess,2017,23(5):20898-20907.
[6] WANG Q,MAO Z,WANG B,et al.Knowledge graph embedding:a survey of approaches and applications[J].IEEE Transactions on Knowledge and Data Engineering,2017,29(12):2724-2743.
[7] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of NIPS’13.Cambridge,USA:MIT Press,2013:2787-2795.
[8] WANG Zhen,ZHANG Jianwen,FENG Jianlin,et al.Knowlegde graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI,2014:1112-1119.
[9] XIAO H,HUANG M,HAO Y,et al.TransA:an adaptive approach for knowledge graph embedding[EB/OL].[2019-02-10].https://arxiv.org/pdf/1509.05490.pdf.
[10] XIAO Han,HUANG Minlie,HAO Yu,et al.TransG:a generative mixture model for knowledge graph embedding[EB/OL].[2019-02-10].https://arxiv.org/pdf/1509.05488v2.pdf.
[11] LIN Yankai,LIU Zhiyuan,SUN Maosong,et al.Learing entity and relation embedding for knowledge graph completion[C]//Proceedings of AAAI’15.[S.l.]:AAAI Press,2015:256-263.
[12] JI G,HE S,XU L,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Washington D.C.,USA:IEEE Press,2015:687-696.
[13] JI G,LIU K,HE S,et al.Knowledge graph completion with adaptive sparse transfer matrix[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press,2016:985-991.
[14] FAN M,ZHOU Q,CHANG E,et al.Transition-based knowledge graph embedding with relational mapping properties[EB/OL].[2019-02-10].http://pdfs.semanticscholar.org/0ddd/f37145689e5f2899f8081d9971882e6ff1e9.pdf.
[15] FENG J,HUANG M,WANG M,et al.Knowledge graph embedding by flexible translation[C]//Proceedings of the 15th International Conference on Principles of Knowledge Representation and Reasoning.[S.l.]:AAAI Press,2016:557-560.
[16] LAO N,MITCHELL T,COHEN W W.Random walk inference and learning in a large scale knowledge base[C]//Proceedings of EMNLP’11.Stroudsburg,USA:ACL,2011:529-539.
[17] LIN Y,LIU Z,LUAN H,et al.Modeling relation paths for representation learning of knowledge bases[EB/OL].[2019-02-10].http://www.emnlp2015.org/proceedings/EMNLP/pdf/EMNLP082.pdf.
[18] BORDES A,GLOROT X,WESTON J,et al.A semantic matching energy function for learning with multi-relational data[J].Machine Learning,2014,94(2):233-259.
[19] BORDES A,GLOROT X,WESTON J,et al.Joint learning of words and meaning representation for open-text semantic parsing[C]//Proceedings of AISTATS’12.Cadiz,Spain:JMLR,2012:127-135.
[20] NICKEL M,TRESP V,KRIEGEL H.A three-way model for collective learning on multi-relational data[C]//Proceedings of ICML’11.New York,USA:ACM Press,2011:809-816.
[21] NICKEL M,TRESP V,KRIEGEL H.Factorizing YAGO:scalable machine learing for linked data[C]//Proceedings of WWW’12.New York,USA:ACM Press,2012:271-280.
[22] SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of NIPS’13.Cambridge,USA:MIT Press,2013:926-934.
[23] ZHAI Sheping,GUO Lin,GAO Shan,et al.A knowledge map completion method using Bayesian reasoning[J].Journal of Chinese Computer Systems,2018,39(5):995-999.(in Chinese)翟社平,郭琳,高山,等.一种采用贝叶斯推理的知识图谱补全方法[J].小型微型计算机系统,2018,39(5):995-999.
[24] WANG Zhitao,CHEN Chengyao,LI Wenjie.Predictive network representation learning for link prediction[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2017:969-972.

选择文件类型/文献管理软件名称

选择包含的内容