基于神经网络的知识推理研究综述
|
摘要
知识推理是知识图谱补全的重要手段,一直以来都是知识图谱领域的研究热点之一。随着神经网络不断取得新的发展,其在知识推理中的应用在近几年逐渐得到广泛重视。基于神经网络的知识推理方法具备更强的推理能力和泛化能力,对知识库中实体、属性、关系和文本信息的利用率更高,推理效果更好。简要介绍知识图谱及知识图谱补全的相关概念,阐述知识推理的概念及基本原理,从语义、结构和辅助存储三个维度展开,综述当下基于神经网络的知识推理最新研究进展,总结了基于神经网络的知识推理在理论、算法和应用方面存在的问题和发展方向。
Knowledge reasoning is an important means of knowledge graph completion and has always been one of the research hotspots in the field of knowledge graph. With the development of neural network, its applications in knowledge reasoning have been paid more and more attention in recent years. The knowledge reasoning methods based on neural network have not only stronger reasoning and generalization abilities, but also higher utilization rates of entities, attributes,relations and text information in the knowledge base. These methods are more effective in reasoning. The relevant concepts of knowledge graph and knowledge graph completion are introduced, the concepts and basic principles of knowledge reasoning are indicated, and then the latest research progresses of the technology of knowledge reasoning based on neural network are reviewed. The existing problems and development directions of knowledge reasoning in the aspect of theory, algorithm and application are summarized.
Knowledge reasoning is an important means of knowledge graph completion and has always been one of the research hotspots in the field of knowledge graph. With the development of neural network, its applications in knowledge reasoning have been paid more and more attention in recent years. The knowledge reasoning methods based on neural network have not only stronger reasoning and generalization abilities, but also higher utilization rates of entities, attributes,relations and text information in the knowledge base. These methods are more effective in reasoning. The relevant concepts of knowledge graph and knowledge graph completion are introduced, the concepts and basic principles of knowledge reasoning are indicated, and then the latest research progresses of the technology of knowledge reasoning based on neural network are reviewed. The existing problems and development directions of knowledge reasoning in the aspect of theory, algorithm and application are summarized.
引文
[1]Bollacker K,Evans C,Paritosh P,et al.Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMODInternational Conference on Management of Data.New York:ACM,2008:1247-1250.
[2]Auer S,Bizer C,Kobilarov G,et al.DBpedia:a nucleus for a web of open data[C]//Proceedings of the 6th International Semantic Web Conference.Berlin,Heidelberg:Springer,2007:722-735.
[3]丁建辉,贾维嘉.知识图谱补全算法综述[J].信息通信技术,2018(1):57-62.
[4]官赛萍,靳小龙,贾岩涛,等.面向知识图谱的知识推理研究进展[J].软件学报,2018,29(10):74-102.
[5]Tari L.Knowledge inference[M].New York:Springer,2013.
[6]Russell S J,Norvig P.Artificial intelligence:a modern approach[J].Applied Mechanics&Materials,2010,263(5):2829-2833.
[7]Kompridis N.So we need something else for reason to mean[J].International Journal of Philosophical Studies,2000,8(3):271-295.
[8]漆桂林,高桓,吴天星.知识图谱研究进展[J].情报工程,2017,3(1):4-25.
[9]徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.
[10]刘峤,李杨,段宏,等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):582-600.
[11]Lao N,Cohen W W.Relational retrieval using a combination of path-constrained random walks[J].Machine Learning,2010,81(1):53-67.
[12]Socher R,Chen D,Manning C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc,2013:926-934.
[13]Chen Danqi,Socher R,Manning C D,et al.Learning new facts from knowledge bases with neural tensor networks and semantic word vectors[J].Computer Science,2013,11(1):392-399.
[14]Bordes A,Usunier N,Garcia-Duran A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc,2013:2787-2795.
[15]Wang Z,Zhang J,Feng J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Twenty-eighth AAAIConference on Artificial Intelligence,2014.
[16]Lin Y,Liu Z,Sun M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of AAAI.Menlo Park,CA:AAAI,2015.
[17]Shi B,Weninger T.Proj E:embedding projection for knowledge graph completion[C]//Proceedings of the 31st AAAIConference on Artificial Intelligence,Menlo Park,CA,2017:1236-1242.
[18]Xie Ruobing,Liu Z,Jia J,et al.Representation learning of knowledge graphs with entity descriptions[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.Menlo Park,CA:AAAI,2016:2659-2665.
[19]Tay Y,Tuan L A,Phan M C,et al.Multi-task neural network for non-discrete attribute prediction in knowledge graphs[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management,2017:1029-1038.
[20]Shi B,Weninger T.Open-world knowledge graph completion[J].Computer Science,2017,5(2):22-31.
[21]王奋昊.大规模知识图谱技术[J].中国计算机学会通讯,2014,3(10):64-68.
[22]Lukovnikov D,Fischer A,Lehmann J,et al.Neural networkbased question answering over knowledge graphs on word and character level[C]//International World Wide Web Conference Committee(IW3C2),Perth,Australia,2017.
[23]Schlichtkrull M,Kipf T N,Bloem P,et al.Modeling relational data with graph convolutional networks[J].arXiv preprint arXiv:1703.06103,2017.
[24]Yang B,Yih W T,He X,et al.Embedding entities and relations for learning and inference in knowledge bases[C]//Proceesings of the International Conference on Learning Representations,2015:233-240.
[25]Neelakantan A,Roth B,Mccallum A.Compositional vector space models for knowledge base completion[J].Computer Science,2015:1-16.
[26]Lin Y,Liu Z,Sun M.Modeling relation paths for representation learning of knowledge bases[J].arXiv preprint arXiv:1506.00379,2015.
[27]Das R,Neelakantan A,Belanger D,et al.Chains of reasoning over entities,relations,and text using recurrent neural networks[C]//Conference of the European Chapter of the Association for Computational Linguistics,2017.
[28]Shen Y,Huang P S,Chang M W,et al.Modeling largescale structured relationships with shared memory for knowledge base completion[C]//Proceedings of the 2nd Workshop on Representation Learning for NLP.ACL,2017:57-68.
[29]Graves A,Wayne G,Reynolds M,et al.Hybrid computing using a neural network with dynamic external memory[J].Nature,2016,538(7626):471-476.
[30]Greff K,Srivastava R K,Koutník J,et al.LSTM:a search space odyssey[J].IEEE Transactions on Neural Networks&Learning Systems,2016,28(10):2222-2232.
[31]Gers F A,Schmidhuber E.LSTM recurrent networks learn simple context-free and context-sensitive languages[J].IEEE Transactions on Neural Networks,2001,12(6):1333-1340.
[32]Wang Z,Chen T,Ren J,et al.Deep reasoning with knowledge graph for social relationship understanding[J].arXiv preprint arXiv:1807.00504,2018.
[33]Scarselli F,Gori M,Tsoi A C,et al.The graph neural network model[J].IEEE Transactions on Neural Networks,2009,20(1):61.
[34]Ren S,He K,Girshick R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems,2015.
[2]Auer S,Bizer C,Kobilarov G,et al.DBpedia:a nucleus for a web of open data[C]//Proceedings of the 6th International Semantic Web Conference.Berlin,Heidelberg:Springer,2007:722-735.
[3]丁建辉,贾维嘉.知识图谱补全算法综述[J].信息通信技术,2018(1):57-62.
[4]官赛萍,靳小龙,贾岩涛,等.面向知识图谱的知识推理研究进展[J].软件学报,2018,29(10):74-102.
[5]Tari L.Knowledge inference[M].New York:Springer,2013.
[6]Russell S J,Norvig P.Artificial intelligence:a modern approach[J].Applied Mechanics&Materials,2010,263(5):2829-2833.
[7]Kompridis N.So we need something else for reason to mean[J].International Journal of Philosophical Studies,2000,8(3):271-295.
[8]漆桂林,高桓,吴天星.知识图谱研究进展[J].情报工程,2017,3(1):4-25.
[9]徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.
[10]刘峤,李杨,段宏,等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):582-600.
[11]Lao N,Cohen W W.Relational retrieval using a combination of path-constrained random walks[J].Machine Learning,2010,81(1):53-67.
[12]Socher R,Chen D,Manning C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc,2013:926-934.
[13]Chen Danqi,Socher R,Manning C D,et al.Learning new facts from knowledge bases with neural tensor networks and semantic word vectors[J].Computer Science,2013,11(1):392-399.
[14]Bordes A,Usunier N,Garcia-Duran A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of Advances in Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc,2013:2787-2795.
[15]Wang Z,Zhang J,Feng J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Twenty-eighth AAAIConference on Artificial Intelligence,2014.
[16]Lin Y,Liu Z,Sun M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of AAAI.Menlo Park,CA:AAAI,2015.
[17]Shi B,Weninger T.Proj E:embedding projection for knowledge graph completion[C]//Proceedings of the 31st AAAIConference on Artificial Intelligence,Menlo Park,CA,2017:1236-1242.
[18]Xie Ruobing,Liu Z,Jia J,et al.Representation learning of knowledge graphs with entity descriptions[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.Menlo Park,CA:AAAI,2016:2659-2665.
[19]Tay Y,Tuan L A,Phan M C,et al.Multi-task neural network for non-discrete attribute prediction in knowledge graphs[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management,2017:1029-1038.
[20]Shi B,Weninger T.Open-world knowledge graph completion[J].Computer Science,2017,5(2):22-31.
[21]王奋昊.大规模知识图谱技术[J].中国计算机学会通讯,2014,3(10):64-68.
[22]Lukovnikov D,Fischer A,Lehmann J,et al.Neural networkbased question answering over knowledge graphs on word and character level[C]//International World Wide Web Conference Committee(IW3C2),Perth,Australia,2017.
[23]Schlichtkrull M,Kipf T N,Bloem P,et al.Modeling relational data with graph convolutional networks[J].arXiv preprint arXiv:1703.06103,2017.
[24]Yang B,Yih W T,He X,et al.Embedding entities and relations for learning and inference in knowledge bases[C]//Proceesings of the International Conference on Learning Representations,2015:233-240.
[25]Neelakantan A,Roth B,Mccallum A.Compositional vector space models for knowledge base completion[J].Computer Science,2015:1-16.
[26]Lin Y,Liu Z,Sun M.Modeling relation paths for representation learning of knowledge bases[J].arXiv preprint arXiv:1506.00379,2015.
[27]Das R,Neelakantan A,Belanger D,et al.Chains of reasoning over entities,relations,and text using recurrent neural networks[C]//Conference of the European Chapter of the Association for Computational Linguistics,2017.
[28]Shen Y,Huang P S,Chang M W,et al.Modeling largescale structured relationships with shared memory for knowledge base completion[C]//Proceedings of the 2nd Workshop on Representation Learning for NLP.ACL,2017:57-68.
[29]Graves A,Wayne G,Reynolds M,et al.Hybrid computing using a neural network with dynamic external memory[J].Nature,2016,538(7626):471-476.
[30]Greff K,Srivastava R K,Koutník J,et al.LSTM:a search space odyssey[J].IEEE Transactions on Neural Networks&Learning Systems,2016,28(10):2222-2232.
[31]Gers F A,Schmidhuber E.LSTM recurrent networks learn simple context-free and context-sensitive languages[J].IEEE Transactions on Neural Networks,2001,12(6):1333-1340.
[32]Wang Z,Chen T,Ren J,et al.Deep reasoning with knowledge graph for social relationship understanding[J].arXiv preprint arXiv:1807.00504,2018.
[33]Scarselli F,Gori M,Tsoi A C,et al.The graph neural network model[J].IEEE Transactions on Neural Networks,2009,20(1):61.
[34]Ren S,He K,Girshick R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems,2015.