Advertisement

Category-Embodied Knowledge Embedding

  • Maoyuan Zhang
  • Qi Wang
  • Zhou Xu
  • Jianping Zhu
  • Shuyuan Sun
  • Yang Wen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11303)

Abstract

Knowledge graph (KG) embedding, which transforms both the entities and relations into continuous low-dimensional continuous vector space, has attracted considerable research. A large amount of models have been proposed for knowledge graph embedding. However, most previous approaches only regard the knowledge graph as a set of triples, ignoring the categories of the entities. In this paper, we take advantages of category information by modelling the category-specific embedding. Specially, we see the interaction between the category embedding and KG embedding as a closed loop, in which the category embedding and KG embedding are promoted mutually. Triples along with their categories are represented in a unified framework, in which way the embedding of triples are category-aware. We evaluate our model on multiple real-world KGs, and it show impressive improvements on link prediction and triple classification compared with other baselines.

Keywords

Distributed representation Knowledge graph representation 

Notes

Acknowledgments

The authors would like to acknowledge the support provided by the Research Planning Project of National Language Committee (No. YB135-40) and the Humanity and Social Science Youth Foundation of Ministry of Education of China (No. 15YJC870029).

References

  1. 1.
    Kurt, B., Colin, E., Praveen, P., Tim, S., Jamie, T.: Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD Conference 2008, pp. 1247–1250 (2008)Google Scholar
  2. 2.
    Antoine, B., Sumit, C., Jason, W.: Question answering with subgraph embeddings. In: Computer Science, pp. 615–620 (2014)Google Scholar
  3. 3.
    Antoine, B., Nicolas, U., Alberto, G., Jason, W., Yakhnenko, O.: Translating embeddings for modeling multi-relational Data. In: Advances in Neural Information Processing Systems 2013, pp. 2787–2795 (2013)Google Scholar
  4. 4.
    Antoine, B., Jason, W., Ronan, C., Yoshua, B.: Learning structured embeddings of knowledge bases. In: AAAI Conference on Artificial Intelligence 2011, pp. 301–306 (2011)Google Scholar
  5. 5.
    Cao, S., Lu, W., Xu, Q.: GraRep: learning graph representations with global structural information. In: ACM International on Conference on Information and Knowledge Management 2015, pp. 891–900 (2015)Google Scholar
  6. 6.
    Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: AAAI Conference on Artificial Intelligence 2010, pp. 1306–1313 (2010)Google Scholar
  7. 7.
    Cavallari, S., Zheng, V., Cai, H., Chang, C., Cambria, E.: Learning community embedding with community detection and node embedding on graphs. In: ACM on Conference on Information and Knowledge Management 2017, pp. 377–386 (2017)Google Scholar
  8. 8.
    Guo, S., Wang, Q., Wang, L., Wang, L., Guo, L.: SSE: semantically smooth embedding for knowledge graphs. IEEE Trans. Knowl. Data Eng. 29(4), 884–897 (2017)CrossRefGoogle Scholar
  9. 9.
    Lehmann, J.: DBpedia: a large-scale, multilingual knowledge base extracted from wikipedia. Semant. Web 6(2), 167–195 (2015)Google Scholar
  10. 10.
    Lin, L., Liu, Z., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI Conference on Artificial Intelligence 2015, pp. 2181–2187 (2015)Google Scholar
  11. 11.
    Maximilian, N., Volker, T., Hans, P.: Factorizing YAGO: scalable machine learning for linked data. In: International World Wide Web Conference 2012, pp. 271–280 (2012)Google Scholar
  12. 12.
    Szumlanski, S., Gomez, F.: Automatically acquiring a semantic network of related concepts. In: ACM on Conference on Information and Knowledge Management 2010, pp. 19–28 (2010)Google Scholar
  13. 13.
    Tanev, H.: A WordNet-based approach to named entities recognition. In: The Workshop on Building and Using Semantic Networks, Association for Computational Linguistics 2002, pp. 1–7 (2002)Google Scholar
  14. 14.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Association for the Advancement of Artificial Intelligence 2014, pp. 1112–1119 (2014)Google Scholar
  15. 15.
    Xiao, H., Huang, M., Hao, Y., Zhu, X.: TransG: a generative mixture model for knowledge graph embedding. In: Computer Science, pp. 2316–2325 (2015)Google Scholar
  16. 16.
    Xie, R., Liu, Z., Jia, J., Luan, H., Sun, M.: Representation learning of knowledge graphs with entity descriptions. In: International Joint Conference on Artificial Intelligence 2016, pp. 2659–2665 (2016)Google Scholar
  17. 17.
    Xie, R., Liu, Z., Sun, M.: Representation learning of knowledge graphs with hierarchical types. In: International Joint Conference on Artificial Intelligence 2016, pp. 2965–2971 (2016)Google Scholar
  18. 18.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: AAAI-Association for the Advancement of Artificial Intelligence 2014, pp. 1112–1119 (2014)Google Scholar
  19. 19.
    Krompaß, D., Baier, S., Tresp, V.: Type-constrained representation learning in knowledge graphs. In: Arenas, M., et al. (eds.) ISWC 2015. LNCS, vol. 9366, pp. 640–655. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-25007-6_37CrossRefGoogle Scholar
  20. 20.
    Wang, Q., Mao, Z., Wang, B., Guo, L.: Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29(12), 2724–2743 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Maoyuan Zhang
    • 1
  • Qi Wang
    • 1
  • Zhou Xu
    • 2
    • 3
  • Jianping Zhu
    • 1
  • Shuyuan Sun
    • 1
  • Yang Wen
    • 1
  1. 1.School of ComputerCentral China Normal UniversityWuhanPeople’s Republic of China
  2. 2.School of Computer ScienceWuhan UniversityWuhanPeople’s Republic of China
  3. 3.Department of ComputingThe Hong Kong Polytechnic UniversityKowloonHong Kong

Personalised recommendations