基于知识表示学习的知识可信度评估

doi:10.19678/j.issn.1000-3428.0057891

摘要/Abstract

摘要： 知识图谱自动化构建技术的发展以及信息量的增加导致知识图谱中引入了噪声和冲突，为了有效应用知识图谱，需要对知识的可信度进行评估。建立一种基于知识表示学习的知识可信度评估模型PTCA，利用实体之间的关联强度、实体类型信息以及多步路径信息对知识的可信度进行计算。通过三元组分类、知识图谱噪声检测以及知识图谱补全等3个任务对模型性能进行测试，结果表明，PTCA模型可以检测知识图谱内部存在的噪声和冲突，对三元组知识的可信度进行有效计算，且在有噪声干扰的数据集上的评估性能优于CKRL和PTransE模型。

关键词: 知识图谱, 知识表示学习, 知识可信度评估, 三元组可信度评估, 噪声检测

Abstract: The developing automated construction technology and the growing amount of information have introduced noises and conflicts into knowledge graph.For this reason,the evaluation of knowledge credibility is required to better support the application of knowledge graph.Based on knowledge representation learning,this paper designs a knowledge credibility evaluation model,PTCA,which calculates the knowledge credibility based on the strength of the correlation between entities,entity type information,and multi-step path information.The model has been tested with multiple tasks,including the triplet classification task,the noise detection task for knowledge graph,and the knowledge graph completion task.Experimental results show that the model can detect the noises and conflicts existing in the knowledge graph,as well as effectively calculate the credibility of triplets.It demonstrates better evaluation performance on noisy datasets than CKRL and the PTransE benchmark model.

Key words: knowledge graph, knowledge representation learning, knowledge credibility evaluation, triplet credibility evaluation, noise detection

中图分类号:

TP182

张晓明, 孙维雅, 王会勇. 基于知识表示学习的知识可信度评估[J]. 计算机工程, 2021, 47(7): 44-54.

ZHANG Xiaoming, SUN Weiya, WANG Huiyong. Evaluation of Knowledge Credibility Based on Knowledge Representation Learning[J]. Computer Engineering, 2021, 47(7): 44-54.

https://www.ecice06.com/CN/Y2021/V47/I7/44

图/表 8

20210720203029

20210720203032

20210720203036

20210720203040

20210720203044

20210720203048

20210720203051

20210720203055

参考文献

[1] LEHMANN J,ISELE R,JAKOB M,et al.DBpedia-a large-scale,multilingual knowledge base extracted from Wikipedia[J].Semantic Web,2015,6(2):167-195.
[2] BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of SIGMOD Conference.Washington D.C.,USA:IEEE Press,2008:1247-1250.
[3] WU W,LI H,WANG H,et al.Probase:a probabilistic taxonomy for text understanding[C]//Proceedings of ACM International Conference on Management of Data.New York,USA:ACM Press,2012:481-492.
[4] XIN D,EVGENIY G,GEREMY H,et al.Knowledge vault:a Web-scale approach to probabilistic knowledge fusion[EB/OL].[2020-01-05].https://www.cs.ubc.ca/~murphyk/papers/kv-kdd14.pdf.
[5] JIA S B,XIANG Y,CHEN X J,et al.TTMF:a triple trustworthiness measurement frame for knowledge graphs[EB/OL].[2020-01-05].https://arxiv.org/pdf/1809.09414.pdf.
[6] XIE R,LIU Z,LIN F,et al.Does William Shakespeare really write Hamlet? Knowledge representation learning with confidence[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press,2018:4954-4961.
[7] SHAN Y,BU C LIU X,et al.Confidence-aware negative sampling method for noisy knowledge graph embedding[C]//Proceedings of 2018 IEEE International Conference on Big Knowledge.Washington D.C.,USA:IEEE Press,2018:33-40.
[8] ZHAO Y,LIU J.SCEF:a support-confidence-aware embedding framework for knowledge graph refinement[EB/OL].[2020-01-05].https://arxiv.org/pdf/1902.06377.pdf.
[9] MINERVINI P,COSTABELLO L,E MUÑO Z,et al.Regularizing knowledge graph embeddings via equivalence and inversion axioms[C]//Proceedings of Joint European Conference on Machine Learning & Knowledge Discovery in Databases.Berlin,Germany:Springer,2017:668-683.
[10] 陈曦,陈华钧,张文.规则增强的知识图谱表示学习方法[J].情报工程,2017,3(1):26-34. CHEN X,CHEN H J,ZHANG W.Rule-enhanced knowledge graph representation learning method[J].Information Engineering,2017,3(1):26-34.(in Chinese)
[11] SHU G,QUAN W,WANG L,et al.Knowledge graph embedding with iterative guidance from soft rules[EB/OL].[2020-01-05].https://arxiv.org/pdf/1711.11231.pdf.
[12] 赵振,胡乃平,刘敏,等.基于本体可信模型的知识可信评价理论[J].计算机集成制造系统,2014,20(11):2904-2914. ZHAO Z,HU N P,LIU M,et al.Theory of knowledge trustworthiness evaluation based on ontology trust model[J].Computer Integrated Manufacturing System,2014,20(11):2904-2914.(in Chinese)
[13] BIZER C,OLDAKOWSKI R.Using context- and content-based trust policies on the semantic Web[C]//Proceedings of International Conference on World Wide Web.New York,USA:ACM Press,2004:228-229.
[14] JINGWEI H,MARK S.Fox:an ontology of trust:formal semantics and transitivity[EB/OL].[2020-01-05].https://www.site.uottawa.ca/~nelkadri/CSI5389/Papers/122-Ontology%20of%20Trust.pdf.
[15] LAO N,MITCHELL T M,COHEN W W.Random walk inference and learning in a large scale knowledge base[C]//Proceedings of 2011 Conference on Empirical Methods in Natural Language Processing.[S.l.]:AAAI Press,2011:152-163.
[16] RICHARDSON M,DOMINGOS P.Markov logic networks[J].Machine Learning,2006,62(1/2):107-136.
[17] ANTOINE B,NICOLAS U,ALBERTO G D,et al.Translating embeddings for modeling multi-relational data[EB/OL].[2020-01-05].http://thespermwhale.com/jaseweston/papers/CR_paper_nips13.pdf.
[18] WANG Z,ZHANG J W,FENG J L,et al.Knowledge graph embedding by translating on hyperplanes[EB/OL].[2020-01-05].https://persagen.com/files/misc/wang2014knowledge.pdf.
[19] LIN Y K,LIU Z Y,SUN M S,et al.Learning entity and relation embeddings for knowledge graph completion[EB/OL].[2020-01-05].http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf.
[20] JI G,HE S,XU L,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of Meeting of the Association for Computational Linguistics & the International Joint Conference on Natural Language Processing.New York,USA:ACM Press,2015:687-696.
[21] 李鑫超,李培峰,朱巧明.一种基于改进向量投影距离的知识图谱表示方法[J].计算机科学,2020,47(4):189-193. LI X C,LI P F,ZHU Q M.Knowledge graph representation based on improved vector projection distance[J].Computer Science,2020,47(4):189-193.(in Chinese)
[22] XIE R,LIU Z,SUN M.Representation learning of knowledge graphs with hierarchical types[C]//Proceedings of International Joint Conference on Artificial Intelligence.[S.l.]:AAAI Press,2016:125-136.
[23] LIN Y,LIU Z,LUAN H,et al.Modeling relation paths for representation learning of knowledge bases[J].Computer Science,2015,8:705-714.

选择文件类型/文献管理软件名称

选择包含的内容