Abstract
Knowledge graph embedding (KGE) models focus only on the characteristics of the datasets, ignoring the relation semantics. Most of KGEs have no ability to handle dataset with large numbers of symmetric relations. Formalization and experimentation given in this paper clearly shows the existence of the aforementioned problem, since we propose KGE bi-vector models which represent each symmetric relation as vector pair. In the vector addition of entities and relations, the vector of bi-vector that is closer to the result is selected as the train/test vector. Symmetric information contained in the two symmetric edges is lossless in bi-vector models. We generate the benchmark datasets based on FB15k and WN18 by completing the symmetric relation triples to verify models. The experimental results of our models clearly affirm the effectiveness and superiority of our models against baseline.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, the threshold is set to 0.5.
References
Bordes A, Usunier N, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. In: NIPS
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: AAAI
Ji G, He S, Xu L, Liu K, Zhao J (2015) Knowledge graph embedding via dynamic mapping matrix. In: ACL
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: AAAI
Ji G, Liu K, He S, Zhao J (2016) Knowledge graph completion with adaptive sparse transfer matrix. In: Thirtieth AAAI conference on artificial intelligence
Yang B, Yih W, He X, Gao J, Deng L (2015) Embedding entities and relations for learning and inference in knowledge bases. In: ICLR
Nickel M, Rosasco L, Poggio T (2016) Holographic embeddings of knowledge graphs. In: AAAI
Nickel M, Tresp V, Kriegel HP (2011) A three-way model for collective learning on multi-relational data. In: ICML, vol 11, pp 809–816, June 2011
Welbl J, Riedel S, Bouchard G (2016) Complex embeddings for simple link prediction. In: ICML
Bordes, A, Weston J, Collobert R, Bengio Y (2012) Learning structured embeddings of knowledge bases. In: AAAI
Socher R, Chen D, Manning CD, Ng AY (2013) Reasoning with neural tensor networks for knowledge base completion. In: NIPS
Bordes A, Glorot X, Weston J (2012) Joint learning of words and meaning representations for open-text semantic parsing. In: International conference on artificial intelligence and statistics
Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD
Miller GA (1994) WordNet: a lexical database for English. In: The workshop on human language technology
Han X, Cao S, Lv X. Lin Y, Liu Z, Sun M, Li J (2018) OpenKE: an open toolkit for knowledge embedding. In: Proceedings of EMNLP
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yao, J., Zhao, Y. (2020). Knowledge Graph Embedding Bi-vector Models for Symmetric Relation. In: Jia, Y., Du, J., Zhang, W. (eds) Proceedings of 2019 Chinese Intelligent Systems Conference. CISC 2019. Lecture Notes in Electrical Engineering, vol 594. Springer, Singapore. https://doi.org/10.1007/978-981-32-9698-5_4
Download citation
DOI: https://doi.org/10.1007/978-981-32-9698-5_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9697-8
Online ISBN: 978-981-32-9698-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)