CHEN Xinyuan,XIE Shengyi,CHEN Qingqiang,et al.Knowledge base Completion based on Temporal Mapping and CNN[J].Journal of Chengdu University of Information Technology,2022,37(01):55-61.[doi:10.16836/j.cnki.jcuit.2022.01.010]
结合时间映射和卷积神经网络的知识补全
- Title:
- Knowledge base Completion based on Temporal Mapping and CNN
- 文章编号:
- 2096-1618(2022)01-0055-07
- 分类号:
- TP18
- 文献标志码:
- A
- 摘要:
- 现有知识库存在大量缺失事实且事实常携带时间信息。针对主流嵌入表示方法在知识补全时常忽略时间维度的问题,设计一种时间敏感的三元组嵌入表示方法TSKGC(time sensitive knowledge graph completion)。通过为时间戳分配超平面,将时序信息合并到实体关系空间中,并进一步将映射后三元组的3列k维矩阵表示用作卷积神经网络的输入,在不同超平面对应的多通道中并行处理,提取三元组特征用于知识补全。在YAGO11k和Wikidata12k数据集上的实验证明,TSKGC具备一定的时间预测能力,并能有效利用时间信息提高链路预测的性能表现,特别在1-M、M-1和M-M复杂关系类型上相比主流模型具备一定优势。
- Abstract:
- There are a lot of missing facts in the existing knowledge inventory, and the facts often carry time information. Aiming at the problem that the time dimension is often ignored in the knowledge completion of mainstream embedded representation methods, a time sensitive knowledge graph completion method(TSKGC)is designed. By assigning hyperplanes to the timestamp, the time series information is merged into the entity relation space, and the three-column k-dimensional matrix representation of the mapped triple is further used as the input of the convolution neural network(CNN). In parallel processing in multi-channels corresponding to different hyperplanes, and triplet features are extracted for knowledge completion. Experiments on YAGO11k and Wikidata12k datasets show that TSKGC has a certain time prediction ability, and can effectively use time information to improve the performance of link prediction, especially in 1-M,M-1 and M-M complex relationship types have certain advantages compared with mainstream models.
参考文献/References:
[1] Mitchell T,Cohen W,Hruschka E,et al.Never-ending Learning[J].Communications of the ACM,2018,61(5):103-115.
[2] Rebele T,Suchanek F,Hoffart J,et al.YAGO:A multilingual knowledge base from wikipedia,wordnet, and geonames[C].International Semantic Web Conference.Cham:Springer,2016:177-185.
[3] Bollacker K,Evans C,Paritosh P,et al.Freebase:A Collaboratively Created Graph Database for Structuring Human Knowledge[C].Proceedings of the 2008 ACM SIGMOD international conference on Management of data.Vancouver:ACM,2008:1247-1250.
[4] Xiong C,Callan J.Query Expansion with Freebase[C].Proceedings of the 2015 international conference on the theory of information retrieval.New York:ACM,2015:111-120.
[5] Dong L,Wei F,Zhou M,et al.Question Answering over Freebase with Multi-column Convolutional Neural Networks[C].Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).Beijing:ACL,2015:260-269.
[6] Bordes A,Usunier N,Chopra S,et al.Large-scale Simple Question Answering with Memory Networks[EB/OL].arXiv preprint arXiv:1506.02075,2015.
[7] Hao Y,Zhang Y,Liu K,et al.An End-to-end Model for Question Answering over Knowledge Base with Cross-attention Combining Global Knowledge[C].Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Pennsylvania:ACL,2017:221-231.
[8] Xiong C,Power R,Callan J.Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding[C].Proceedings of the 26th international conference on world wide web.Perth:ACM,2017:1271-1279.
[9] LIU Q,LI Y,DUAN H,et al.Overview of Knowledge Map Construction Technology[J].Computer research and development,2016,53(3):582-600.
[10] West R,Gabrilovich E,Murphy K,et al.Knowledge Base Completion via Search-based Question Answering[C].Proceedings of the 23rd international conference on World wide web.Seoul:ACM,2014:515-526.
[11] LIU Z Y,SUN M S,LIN Y K,et al.Research Progress of Knowledge Representation Learning[J].Computer research and development,2016,53(2):247-261.
[12] Nickel M,Rosasco L,Poggio T.Holographic embeddings of knowledge graphs[C].Proceedings of the AAAI Conference on Artificial Intelligence.Phoenix:AAAI press,2016:30-41.
[13] Dettmers T,Minervini P,Stenetorp P,et al.Convolutional 2D Knowledge Graph Embeddings[C]. national conference on artificial intelligence.New Orleans:AAAI press,2018:1811-1818.
[14] Guo S,Wang Q,Wang L,et al.Knowledge Graph Embedding with Iterative Guidance from Soft Rules[EB/OL].arXiv preprint arXiv:1711.11231,2017.
[15] Erxleben F,Günther M,Krötzsch M,et al.Introducing Wikidata to the Linked Data Web[C].International Semantic Web Conference. Springer.Cham:Spring,2014:50-65.
[16] Jiang T,Liu T,Ge T,et al.Encoding Temporal Information for Time-aware Link Prediction[C].Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Texas:ACL,2016:2350-2354.
[17] Bordes A,Usunier N,Garcia-Duran A,et al.Translating Embeddings for Modeling Multi-relational Data[C].Advances in neural information processing systems.Cancouver:MIT press,2013:2787-2795.
[18] Wang Z,Zhang J,Feng J,et al.Knowledge graph embedding by translating on hyperplanes[C].national conference on artificial intelligence.Vancouver:AAAI press,2014:1112-1119.
[19] Lin Y,Liu Z,Sun M,et al.Learning entity and relation embeddings for knowledge graph completion[C].national conference on artificial intelligence.Texas:AAAI press,2015:2181-2187.
[20] 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(Volume 1:Long Papers).Beijing:ACL,2015:687-696.
[21] Nguyen D Q,Sirts K,Qu L,et al.Stranse: A Novel Embedding Model of Entities and Relationships in Knowledge Bases[EB/OL].arXiv preprint arXiv:1606.08140,2016.
[22] Ji G,Liu K,He S,et al.Knowledge graph completion with adaptive sparse transfer matrix[C].national conference on artificial intelligence.Phoenix:AAAI press,2016:985-991.
[23] 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.
[24] Nickel M,Murphy K,Tresp V,et al.A Review of Relational Machine Learning for Knowledge Graphs[J].Proceedings of the IEEE,2015,104(1):11-33.
[25] Yang B,Yih W,He X,et al.Embedding Entities and Relations for Learning and Inference in Knowledge Bases[EB/OL].arXiv preprint arXiv:1412.6575,2014.
[26] Trouillon T,Welbl J,Riedel S,et al.Complex embeddings for simple link prediction[C].international conference on machine learning.California: IEEE,2016:2071-2080.
[27] Chen D,Socher R,Manning C D,et al.Learning New Facts from Knowledge Bases with Neural Tensor Networks and Semantic Word Vectors[EB/OL].arXiv preprint arXiv:1301.3618,2013.
[28] Nguyen D Q,Sirts K,Qu L,et al.Neighborhood Mixture Model for Knowledge Base Completion[J].arXiv preprint arXiv:1606.06461,2016.
[29] Toutanova K,Lin X V,Yih W,et al.Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text[C].Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Berlin:ACL,2016:1434-1444.
[30] Garcia Duran A,Niepert M.Kblrn:End-to-end Learning of Knowledge Base Representations with Latent,Relational,and Numerical Features[EB/OL].arXiv preprint arXiv:2017:1709.04676.
[31] Nguyen D Q.An Overview of Embedding Models of Entities and Relationships for Knowledge Base Completion[EB/OL].arXiv preprint arXiv:1703.08098,2017.
[32] Toutanova K,Chen D.Observed Versus Latent Features for Knowledge Base and Text Inference[C].Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality.Beijing:ACL,2015:57-66.
[33] Toutanova K,Chen D,Pantel P,et al.Representing Text for Joint Embedding of Text and Knowledge Bases[C].Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Pennsylvania: ACL,2015:1499-1509.
[34] Wang Z,Li J Z.Text-Enhanced Representation Learning for Knowledge Graph[C].Proceedings of International Joint Conference on Artificial Intelligent. New York:IJCAI,2016:1293-1299.
[35] Kim Y.Convolutional Neural Networks for Sentence Classification[EB/OL].arXiv preprint arXiv:1408.5882,2014.
[36] Nguyen D Q,Nguyen D Q,Nguyen T D,et al.A Convolutional Neural Network-based Model for Knowledge Base Completion and Its Application to Search Personalization[J].Semantic Web,2019,10(5):947-960.
[37] Wang Y,Zhu M,Qu L,et al.Timely YAGO:Harvesting,Querying,and Visualizing Temporal Knowledge from Wikipedia[C].Proceedings of the 13th International Conference on Extending Database Technology.New Yokr:ACM,2010:697-700.
[38] UzZaman N,Llorens H,Derczynski L,et al.Semeval-2013 Task 1:Tempeval-3:Evaluating Time Expressions,Events,and Temporal Relations[C].Second Joint Conference on Lexical and Computational Semantics(* SEM), Volume 2:Proceedings of the Seventh International Workshop on Semantic Evaluation(SemEval 2013).Atlanta:ACL,2013:1-9.
[39] Trivedi R,Dai H,Wang Y,et al.Know-evolve:Deep Temporal Reasoning for Dynamic Knowledge Graphs[C].Proceedings of the 34th International Conference on Machine Learning-Volume 70.Sydney:ACM,2017:3462-3471.
[40] Leblay J,Chekol M W.Deriving Validity Time in Knowledge Graph[C].Companion Proceedings of the The Web Conference 2018.Cham:Spring,2018:1771-1776.
[41] Dasgupta S S,Ray S N,Talukdar P.Hyte:Hyperplane-based Temporally Aware Knowledge Graph Embedding[C].Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Doha:ACL,2018:2001-2011.
[42] Mirza P,Tonelli S.Catena:Causal and Temporal Relation Extraction from Natural Language Texts[C].Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics: Technical Papers.Osaka:ACL,2016:64-75.
[43] Mcdowell B,Chambers N,Ororbia A G,et al.Event Ordering with a Generalized Model for Sieve Prediction Ranking[C].international joint conference on natural language processing.Taipei:IJCAI,2017:843-853.
[44] Kingma D P,Ba J.Adam:A Method for Stochastic Optimization[EB/OL].arXiv preprint arXiv:1412.6980,2014.
[45] Nathani D,Chauhan J,Sharma C,et al.Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs[J].arXiv preprint arXiv:1906.01195,2019.
[46] Mahdisoltani F,Biega J,Suchanek F M.Yago3:A Knowledge Base from Multilingual Wikipedias[C].7th biennial conference on innovative data systems research.California:CIDR Conference,2014.13-20.
备注/Memo
收稿日期:2020-11-17
基金项目:福建省教育科学“十三五”规划2020年度课题资助项目(FJJKCG20-402)