基于组合关系翻译的知识表示学习模型
Knowledge Representation Learning Model Based on Composing Relations with Translation
摘要: 目前，基于表示学习的知识图谱嵌入方法旨在将知识图谱中的实体和关系映射到一个低维的向量空间中，例如，翻译模型如TransE及其变体在近年来已显示出可喜的结果，它们将实体与实体之间的关系表示为实体向量之间的平移操作。这些工作中的大多数都专注于对单一关系进行建模，因此没有充分利用知识图谱的图结构信息。在本文中，我们提出了TransE的扩展，它通过添加相应的翻译向量来对关系的组合进行建模。我们的实验结果表明，我们的方法可以提高预测单个关系以及它们的组合的性能。
Abstract: Currently, knowledge graph embedding methods based on representation learning aim to map entities and relations in knowledge graphs into a low-dimensional vector space. For example, translation model such as TransE and its variants have shown promising results in recent years. In translation model, relations of each entity pair are regarded as translation operations between entity vectors. Most of these works focus on modeling a single relation and thus do not fully exploit the graph structure information of knowledge graphs. In this paper, an extension of TransE is purposed, which models the composition of relations by adding the corresponding translation vectors. Our experimental results show that our method can improve the performance of predicting single rela-tions as well as compositions of them.
文章引用：区恩海. 基于组合关系翻译的知识表示学习模型[J]. 计算机科学与应用, 2022, 12(3): 654-661. https://doi.org/10.12677/CSA.2022.123066

参考文献

[1] Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S. and Dean, J. (2013) Distributed Representations of Words and Phrases and Their Compositionality. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z. and Weinberger, K., Eds., Advances in Neural Information Processing Systems, Curran Associates, Inc., Red Hook, 3111-3119.
https://proceedings.neurips.cc/paper/2013/file/9aa42b31882ec039965f3c4923ce901b-Paper.pdf
[2] Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2013) Efficient Estimation of Word Representations in Vector Space.
https://arxiv.org/abs/1301.3781
[3] Yang, B., Yih, W.T., He, X., Gao, J. and Deng, L. (2014) Embedding Entities and Relations for Learning and Inference in Knowledge Bases.
https://arxiv.org/abs/1412.6575
[4] Wang, Z., Zhang, J., Feng, J. and Chen, Z. (2014) Knowledge Graph Embedding by Translating on Hyperplanes. Proceedings of the AAAI Conference on Artificial Intelligence, Québec, 27-31 July 2014, 1112-1119.
[5] Lin, Y., Liu, Z., Sun, M., Liu, Y. and Zhu, X. (2015) Learning Entity and Relation Embeddings for Knowledge Graph Completion. Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, 25-30 January 2015, 2181-2187.
[6] Ji, G., He, S., Xu, L., Liu, K. and Zhao, J. (2015) Knowledge Graph Embedding via Dynamic Mapping Matrix. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Pro-cessing, Beijing, 26-31 July 2015, 687-696.
[7] Nickel, M., Tresp, V. and Kriegel, H.P. (2011) A Three-Way Model for Collective Learning on Multi-Relational Data. Proceedings of the 28th International Conference on International Conference on Machine Learning, Bellevue, 28 June-2 July 2011, 809-816.
[8] Nickel, M., Rosasco, L. and Poggio, T. (2016) Holographic Embeddings of Knowledge Graphs. Proceedings of the Thirtieth AAAI Conference on Artificial Intel-ligence, Phoenix Arizona, 12-17 February 2016, 1955-1961.
[9] Yang, B., Yih, W.T., He, X., Gao, J. and Deng, L. (2014) Embedding Entities and Relations for Learning and Inference in Knowledge Bases. arXiv:1412.6575.
https://arxiv.org/abs/1412.6575
[10] Trouillon, T., Welbl, J., Riedel, S., Gaussier, É. and Bouchard, G. (2016) Complex Embeddings for Simple Link Prediction. Proceedings of the 33rd International Conference on Machine Learn-ing, New York, 19-24 June 2016, 2071-2080.
https://arxiv.org/pdf/1606.06357.pdf
[11] Lv, X., Hou, L., Li, J. and Liu, Z. (2018) Differentiating Concepts and Instances for Knowledge Graph Embedding. arXiv:1811.04588.
[12] Dai, S., Liang, Y., Liu, S., Wang, Y., Shao, W., Lin, X. and Feng, X. (2018) Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion. Proceedings of the 2nd International Conference on Artificial In-telligence: Technologies and Applications (ICAITA), Chengdu, 25-26 March 2018, 202-205.
[13] Rocktäschel, T., Singh, S. and Riedel, S. (2015) Injecting Logical Background Knowledge into Embeddings for Relation Extraction. Pro-ceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Hu-man Language Technologies, Denver, 31 May-5 June 2015, 1119-1129.
[14] Wang, Q., Wang, B. and Guo, L. (2015) Knowledge Base Completion Using Embeddings and Rules. Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, 25-31 July 2015, 1859-1865.
[15] Neelakantan, A., Roth, B. and McCallum, A. (2015) Compositional Vector Space Models for Knowledge Base Completion. arXiv:1504.06662.
[16] Kemp, C., Tenenbaum, J.B., Griffiths, T.L., Yamada, T. and Ueda, N. (2006) Learning Systems of Concepts with an Infinite Relational Model. Proceedings of the Twenty-First National Conference on Artificial Intelligence, Boston, 16–20 July 2006, 381-388.
[17] Miller, K., Jordan, M. and Griffiths, T. (2009) Nonparametric Latent Feature Models for Link Prediction. Advances in Neural Information Processing Systems, 22, 1276-1284.
[18] Sutskever, I., Tenenbaum, J. and Sala-khutdinov, R.R. (2009) Modelling Relational Data Using Bayesian Clustered Tensor Factorization. Advances in Neural Information Processing Systems, 22, 1821-1828.
[19] Zhu, J., Song, J. and Chen, B. (2016) Max-Margin Nonparamet-ric Latent Feature Models for Link Prediction. arXiv:1602.07428.
[20] Singh, A.P. and Gordon, G.J. (2008) Relational Learning via Collective Matrix Factorization. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, 24-27 August 2008, 650-658. [Google Scholar] [CrossRef] 
[21] Nickel, M., Tresp, V. and Kriegel, H.P. (2012) Factorizing YAGO: Scalable Machine Learning for Linked Data. Proceedings of the 21st International Conference on World Wide Web, Lyon, 16-20 April 2012, 271-280. [Google Scholar] [CrossRef] 
[22] Lao, N. and Cohen, W.W. (2010) Relational Retrieval Using a Combination of Path-Constrained Random Walks. Machine Learning, 81, 53-67. [Google Scholar] [CrossRef] 
[23] García-Durán, A., Bordes, A. and Usunier, N. (2014) Effective Blending of Two and Three-Way Interactions for Modeling Multi-Relational Data. In: Calders, T., Esposito, F., Hüller-meier, E. and Meo R., Eds., Machine Learning and Knowledge Discovery in Databases, Springer, Berlin, 434-449. [Google Scholar] [CrossRef]