丁建辉,贾维嘉

• 1:上海交通大学计算机科学与工程系

摘要(Abstract)：

知识图谱补全算法能让知识图谱变得更加完整,目前是人工智能领域的一个研究热点。为了更好地给出补全算法综述,文章按照能否处理新实体或者新关系,将知识图谱补全算法分成两类:静态知识图谱补全算法以及动态知识图谱补全算法。前者仅能处理实体以及关系都是固定的场景,扩展性较差。后者可以处理含有新实体或者新关系的场景,能够构造动态的知识图谱,具有更好的现实意义。文章主要结合相关工作对动态知识图谱补全算法进行系统性的总结,发现动态知识图谱算法的研究热度逐渐增加,如何更好更快地构建动态知识图谱是一个较好的研究点。

关键词(KeyWords)： 人工智能;表示学习;知识图谱;分布式表示

Abstract:

Keywords:

基金项目(Foundation): 国家重点自然科学基金资助项目(61532013)

作者(Author): 丁建辉,贾维嘉

参考文献(References)：

• [1]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]BOLLACKER K D,EVANS C,PARITOSH P,et al.:Freebase:a collaboratively created graph database for structuring human knowledge[C]//the ACM SIGMODInternational Conference on Management of Data,SIGMOD 2008,Vancouver,BC,Canada,June 10-12,2008:1247-1250
• [3]AUER S,BIZER C,KOBILAROV G,et al.DBpedia:ANucleus for a Web of Open Data[C]//The Semantic Web,6th International Semantic Web Conference,2nd Asian Semantic Web Conference,ISWC 2007+Aswc2007,Busan,Korea,2007:722-735
• [4]DONG X,GABRILOVICH E,HEITZ G,et al.Knowledge vault:a web-scale approach to probabilistic knowledge fusion[C]//In:The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,KDD'14,New York,2014:601-610
• [5]BORDES A,USUNIER N.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems 26:27th Annual Conference on Neural Information Processing Systems2013:2787-2795
• [6]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//the Twenty-Eighth AAAI Conference on Artificial Intelligence,Canada,2014:1112-1119
• [7]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//the Twenty-NinthAAAI Conferenceon Artificial Intelligence,2015:2181-2187
• [8]JI G,HE S,XU L,et al.Knowledge graph embedding via dynamic mapping matrix[C]//the 53rd Annual Meeting of the Association for Computational Linguistics and the7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing,Beijing,China,2015:687-696
• [9]XIAO H,HUANG M,MENG L,et al.SSP:Semantic space projection for knowledge graph embedding with text descriptions[C]//the Thirty-First AAAI Conference on Artificial Intelligence,San Francisco,California,USA,2017:3104-3110
• [10]MA S,DING J,JIA W,et al.Transt:Type-based multiple embedding representations for knowledge graph completion[C]//Machine Learning and Knowledge Discovery in Databases-European Conference,ECML-PKDD 2017:717-733
• [11]SHEN Y,HUANG P,CHANG M,et al.Modeling largescale structured relationships with shared memory for knowledge base completion[C]//the 2nd Workshop on Representation Learning for NLP,Rep4NLP@ACL2017:57-68
• [12]JIANG T,LIU T,GE T,et al.Towards time-aware knowledge graph completion[C]//COLING 2016,26th International Conferenceon Computational Linguistics,Japan.2016:1715-1724
• [13]WANG Z,ZHANG J,FENG J,et al.Knowledge graph and text jointly embedding[C]//the 2014 Conference on Empirical Methods in Natural Language Processing,2014:1591-1601
• [14]Tomas Mikolov,Kai Chen,Greg Corrado,et al.Efficient estimation of word representations in vector space[EB/OL].[2018-02-06].https://www.researchgate.net/publication/234131319_Efficient_Estimation_of_Word_Representations_in_Vector_Space
• [15]ZHONG H,ZHANG J,WANG Z,et al.Aligning knowledge and text embeddings by entity descriptions[C]//the 2015Conference on Empirical Methods in Natural Language Processing,2015:267-272
• [16]SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Advancesin Neural Information Processing Systems 26:27th Annual Conference on Neural Information Processing Systems,2013:926-934
• [17]XIE R,LIU Z,JIA J,et al.Representation learning of knowledge graphs with entity descriptions[C]//the Thirtieth AAAI Conference on Artificial Intelligence,2016:2659-2665
• [18]XU J,QIU X,CHEN K,et al.Knowledgegraph representation with jointly structural and textual encoding[C]//the Twenty-Sixth International Joint Conference on Artificial Intelligence,2017:1318-1324
• [19]HAMAGUCHI T,OIWA H,SHIMBO M,et al.Knowledge transfer forout-of-knowledge-baseentities:Agraphneural network approach[C]//the TwentySixth International Joint Conference on Artificial Intelligence,2017:1802-1808
• [20]TAY Y,LUU A T,HUI S C.Non-parametric estimation of multiple embeddings for link prediction on dynamic knowledge graphs[C]//The Thirty-First AAAI Conference on Artificial Intelligence,2017:1243-1249