Skip to main content
SpringerLink
Log in

GTransE: Generalizing Translation-Based Model on Uncertain Knowledge Graph Embedding

  • Conference paper
  • First Online:
Advances in Artificial Intelligence (JSAI 2019)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1128))

Included in the following conference series:

Abstract

This is an extension from a selected paper from JSAI2019. Knowledge graphs are useful for many AI applications. Many recent studies have been focused on learning numerical representations of a knowledge graph in a low-dimensional vector space. Learning representations benefits the deep learning framework for encoding real-world knowledge. However, most of the studies do not consider uncertain knowledge graphs. Uncertain knowledge graphs, e.g., NELL, are valuable because they can express the likelihood of triples. In this study, we proposed a novel loss function for translation-based models, GTransE, to deal with uncertainty on knowledge graphs. Experimental results show that GTransE can robustly learn representations on uncertain knowledge graphs.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 2787–2795 (2013)

    Google Scholar 

  2. Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Hruschka Jr, E.R., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: Proceedings of the AAAI Conference, pp. 1306–1313 (2010)

    Google Scholar 

  3. Chen, X., Chen, M., Shi, W., Sun, Y., Zaniolo, C.: Embedding uncertain knowledge graphs. In: Proceedings of the AAAI Conference, vol. 33, pp. 3363–3370 (2019)

    Article  Google Scholar 

  4. Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: Proceedings of the AAAI Conference, pp. 1811–1818 (2018)

    Google Scholar 

  5. Ebisu, T., Ichise, R.: TorusE: knowledge graph embedding on a lie group. In: Proceedings of the AAAI Conference, pp. 1819–1826 (2018)

    Google Scholar 

  6. Fan, M., Zhou, Q., Zheng, T.F., Grishman, R.: Large margin nearest neighbor embedding for knowledge representation. In: 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 1, pp. 53–59, December 2015

    Google Scholar 

  7. Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 687–696 (2015)

    Google Scholar 

  8. Jia, Y., Wang, Y., Lin, H., Jin, X., Cheng, X.: Locally adaptive translation for knowledge graph embedding. In: Proceedings of the AAAI Conference, pp. 992–998 (2016)

    Google Scholar 

  9. Kertkeidkachorn, N., Ichise, R.: An automatic knowledge graph creation framework from natural language text. IEICE Trans. Inf. Syst. 101(1), 90–98 (2018)

    Article  Google Scholar 

  10. Kingma, D., Adam, J.B.: A method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (2015)

    Google Scholar 

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

    Google Scholar 

  12. Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the AAAI Conference, pp. 2181–2187 (2015)

    Google Scholar 

  13. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 3111–3119 (2013)

    Google Scholar 

  14. Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI Conference, pp. 1112–1119 (2014)

    Google Scholar 

  15. Xiao, H., Huang, M., Zhu, X.: TransG: a generative model for knowledge graph embedding. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 2316–2325 (2016)

    Google Scholar 

  16. Xie, R., Liu, Z., Lin, F., Lin, L.: Does William Shakespeare really write hamlet? Knowledge representation learning with confidence. In: Proceedings of the AAAI Conference (2018)

    Google Scholar 

  17. Xiong, W., Hoang, T., Wang, W.Y.: DeepPath: a reinforcement learning method for knowledge graph reasoning. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 564–573 (2017)

    Google Scholar 

Download references

Acknowledgment

This work was partially supported by the New Energy and Industrial Technology Development Organization (NEDO).

Author information

Authors and Affiliations

  1. National Institute of Advanced Industrial Science and Technology, Tokyo, Japan

    Natthawut Kertkeidkachorn, Xin Liu & Ryutaro Ichise

  2. National Institute of Informatics, Tokyo, Japan

    Ryutaro Ichise

Authors
  1. Natthawut Kertkeidkachorn
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ryutaro Ichise
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Natthawut Kertkeidkachorn .

Editor information

Editors and Affiliations

  1. Department of Systems Innovation, University of Tokyo, Tokyo, Japan

    Yukio Ohsawa

  2. Faculty of Business and Commerce, Kansai University, Osaka, Japan

    Katsutoshi Yada

  3. Nagoya Institute of Technology, Nagoya, Japan

    Takayuki Ito

  4. Graduate School of System Design, Tokyo Metropolitan University, Tokyo, Japan

    Yasufumi Takama

  5. Department of Information and Communication, Tokyo Metropolitan University, Tokyo, Japan

    Eri Sato-Shimokawara

  6. Faculty of Letters, Chiba University, Chiba, Japan

    Akinori Abe

  7. School of Engineering, The University of Tokyo, Tokyo, Japan

    Junichiro Mori

  8. Graduate School of Economics, Osaka University, Toyonaka, Osaka, Japan

    Naohiro Matsumura

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kertkeidkachorn, N., Liu, X., Ichise, R. (2020). GTransE: Generalizing Translation-Based Model on Uncertain Knowledge Graph Embedding. In: Ohsawa, Y., et al. Advances in Artificial Intelligence. JSAI 2019. Advances in Intelligent Systems and Computing, vol 1128. Springer, Cham. https://doi.org/10.1007/978-3-030-39878-1_16

Download citation

Publish with us

Policies and ethics

Search

Navigation