Learning Multi-Relational Semantics Using Neural-Embedding Models.
作者： Li Deng , Jianfeng Gao , Wen-tau Yih , Xiaodong He , Bishan Yang
DOI:
关键词: Embedding 、 Computer science 、 Simple (abstract algebra) 、 Artificial intelligence 、 Task (project management) 、 Machine learning 、 Kripke semantics 、 Theoretical computer science 、 Empirical research 、 Knowledge base 、 Relation (database)
摘要: In this paper we present a unified framework for modeling multi-relational representations, scoring, and learning, conduct an empirical study of several recent embedding models under the framework. We investigate different choices relation operators based on linear bilinear transformations, also effects entity representations by incorporating unsupervised vectors pre-trained extra textual resources. Our results show interesting findings, enabling design simple model that achieves new state-of-the-art performance popular knowledge base completion task evaluated Freebase.
arxiv.org
harvard.edu
128.84.21.199参考文章(30)
Antoine Bordes, Xavier Glorot, Jason Weston, Yoshua Bengio, A semantic matching energy function for learning with multi-relational data neural information processing systems. ,vol. 94, pp. 233- 259 ,(2014) , 10.1007/S10994-013-5363-6
Volker Tresp, Hans-peter Kriegel, Maximilian Nickel, A Three-Way Model for Collective Learning on Multi-Relational Data international conference on machine learning. pp. 809- 816 ,(2011)
Lise Getoor, Ben Taskar, Introduction to statistical relational learning MIT Press. ,(2007)
Ni Lao, Tom Mitchell, William Cohen, None, Random Walk Inference and Learning in A Large Scale Knowledge Base empirical methods in natural language processing. pp. 529- 539 ,(2011)
Matthew Richardson, Pedro Domingos, Markov logic networks Machine Learning. ,vol. 62, pp. 107- 136 ,(2006) , 10.1007/S10994-006-5833-1
Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, Wei Zhang, Knowledge vault: a web-scale approach to probabilistic knowledge fusion knowledge discovery and data mining. pp. 601- 610 ,(2014) , 10.1145/2623330.2623623
Li Deng, Geoffrey Hinton, Brian Kingsbury, New types of deep neural network learning for speech recognition and related applications: an overview international conference on acoustics, speech, and signal processing. pp. 8599- 8603 ,(2013) , 10.1109/ICASSP.2013.6639344
Pedro Domingos, Prospects and challenges for multi-relational data mining Sigkdd Explorations. ,vol. 5, pp. 80- 83 ,(2003) , 10.1145/959242.959252
Dong Yu, Li Deng, Frank Seide, The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 21, pp. 388- 396 ,(2013) , 10.1109/TASL.2012.2227738
Thomas L. Griffiths, Naonori Ueda, Joshua B. Tenenbaum, Takeshi Yamada, Charles Kemp, Learning systems of concepts with an infinite relational model national conference on artificial intelligence. ,vol. 1, pp. 381- 388 ,(2006)