Entity-related paths modeling for knowledge base completion

Abstract

Knowledge bases (KBs) are far from complete, necessitating a demand for KB completion. Among various methods, embedding has received increasing attention in recent years. PTransE, an important approach using embedding method in KB completion, considers multiple-step relation paths based on TransE, but ignores the association between entity and their related entities with the same direct relationships. In this paper, we propose an approach called EPTransE, which considers this kind of association. As a matter of fact, the dissimilarity of these related entities should be taken into consideration and it should not exceed a certain threshold. EPTransE adjusts the embedding vector of an entity by comparing it with its related entities which are connected by the same direct relationship. EPTransE further makes the euclidean distance between them less than a certain threshold. Therefore, the embedding vectors of entities are able to contain rich semantic information, which is valuable for KB completion. In experiments, we evaluated our approach on two tasks, including entity prediction and relation prediction. Experimental results show that our idea of considering the dissimilarity of related entities with the same direct relationships is effective.

Keywords

KB completion / related entity / embedding representation / relation path / translation operation

References

[1] Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J. Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of ACM SIGMOD International Conference on Management of Data. 2008, 1247–1250

[2] Miller G. Wordnet: a lexical database for english. Future Generation Computer Systems, 1995, 38(11): 39–41

[3] Mendes P, Jakob M, Bizer C. DBpedia: a multilingual cross-domain knowledge base. In: Proceedings of the 8th International Conference on Language Resources and Evaluation. 2012, 1813–1817

[4] Wen D, Liu Y, Yuan K, Si S C, Shen Y. Attention-aware path-based relation extraction for medical knowledge graph. In: Proceedings of International Conference on Smart Computing and Communication. 2017, 321–331

[5] Gesmundo A, Hall K. Projecting the knowledge graph to syntactic parsing. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics. 2014, 28–32

[6] Zheng W, Yu J X, Zou L. Question answering over knowledge graphs: question understanding via template decomposition. Proceedings of the VLDB Endowment, 2018, 11(11): 1373–1386

[7] Chen W, Zhang X, Wang T, Yang B, Li Y. Option-aware knowledge graph for political ideology detection. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2017, 3647–3653

[8] Bordes A, Usunier N, Garcia A, Weston J, Yakhnenko O. Translating embeddings for modeling multi-relational data. In: Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013, 2787–2795

[9] Lin Y, Liu Z, Luan H, Sun M, Rao S, Liu S. Modeling relation paths for representation learning of knowledge bases. In: Proceedings of Conference on Empirical Methods in Natural Language Processing. 2015, 705–714

[10] Bordes A, Weston J, Collobert R, Bengio Y. Learning structured embeddings of knowledge bases. In: Proceedings of AAAI Conference on Artificial Intelligence. 2011, 301–306

[11] Bordes A, Glorot X, Weston J, Bengio Y. A semantic matching energy function for learning with multi-relational data. Machine Learning, 2011, 94(2): 233–259

[12] Wang Z, Zhang J, Feng J, Chen Z. Knowledge graph embedding by translating on hyperplanes. In: Proceedings of AAAI Conference on Artificial Intelligence. 2014, 1112–1119

[13] Lin Y, Liu Z, Zhu X. Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of AAAI Conference on Artificial Intelligence. 2015, 2187–2195

[14] Ji G, He S, Xu L, Liu K, Zhao J. Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics. 2015, 687–696

[15] He S, Liu K, Ji G, Zhao J. Learning to represent knowledge graphs with gaussian embedding. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management. 2015, 623–632

[16] Ji G, Liu K, He S, Zhao J. Knowledge graph completion with adaptive sparse transfer matrix. In: Proceedings of AAAI Conference on Artificial Intelligence. 2016, 985–991

[17] Xiao H, Huang M, Zhu X. Transg: a generative model for knowledge graph embedding. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016, 2316–2325

[18] Lin Y, Liu Z, Sun M. Knowledge representation learning with entities, attributes and relations. In: Proceedings of International Joint Conference on Artificial Intelligence. 2016, 2866–2872

[19] Zhu J, Jia Y, Qiao J. Modeling the correlations of relations for knowledge graph embedding. Journal of Computer Science and Technology, 2018, 33(2): 323–334

[20] Zhang M, Wang Q, Xu W, Li W, Sun S. Discriminative path-based knowledge graph embedding for precise link prediction. In: Proceedings of European Conference on Information Retrieval. 2018, 276–288

[21] Lin X, Liang Y, Giunchiglia F, Feng X, Guan R. Relation path embedding in knowledge graphs. Neural Computing and Applications, 2019, 31: 5629–5639

[22] Wang Z, Rong E, Zhuo H, Zhu H. Embedding knowledge graphs based on transitivity and asymmetry of rules. In: Proceedings of Pacific-Asia Conference on Knowledge Discovery and DataMining. 2018, 141–153

RIGHTS & PERMISSIONS

2020 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature