Advertisement

Aligning Knowledge Base and Document Embedding Models Using Regularized Multi-Task Learning

  • Matthias Baumgartner
  • Wen Zhang
  • Bibek Paudel
  • Daniele Dell’Aglio
  • Huajun Chen
  • Abraham Bernstein
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11136)

Abstract

Knowledge Bases (KBs) and textual documents contain rich and complementary information about real-world objects, as well as relations among them. While text documents describe entities in freeform, KBs organizes such information in a structured way. This makes these two information representation forms hard to compare and integrate, limiting the possibility to use them jointly to improve predictive and analytical tasks. In this article, we study this problem, and we propose KADE, a solution based on a regularized multi-task learning of KB and document embeddings. KADE can potentially incorporate any KB and document embedding learning method. Our experiments on multiple datasets and methods show that KADE effectively aligns document and entities embeddings, while maintaining the characteristics of the embedding models.

Notes

Acknowledgements

We would like to thank the SNF Sino Swiss Science and Technology Cooperation Programme program under contract RiC 01-032014, NSFC 61473260/61673338, and the Swiss Re Institute, in particular Axel Mönkeberg, for discussions and financial support.

References

  1. 1.
    Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS, pp. 2787–2795 (2013)Google Scholar
  2. 2.
    Evgeniou, T., Pontil, M.: Regularized multi-task learning. In: KDD, pp. 109–117 (2004)Google Scholar
  3. 3.
    Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP, pp. 1746–1751. ACL (2014)Google Scholar
  4. 4.
    Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML, vol. 32, pp. 1188–1196. JMLR.org (2014)Google Scholar
  5. 5.
    Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI, vol. 15, pp. 2181–2187 (2015)Google Scholar
  6. 6.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)Google Scholar
  7. 7.
    Nickel, M., Murphy, K., Tresp, V., Gabrilovich, E.: A review of relational machine learning for knowledge graphs. Proc. IEEE 104(1), 11–33 (2016)CrossRefGoogle Scholar
  8. 8.
    Nickel, M., Rosasco, L., Poggio, T.A.: Holographic embeddings of knowledge graphs. In: AAAI, pp. 1955–1961. AAAI Press (2016)Google Scholar
  9. 9.
    Ristoski, P., Paulheim, H.: RDF2Vec: RDF graph embeddings for data mining. In: Groth, P. (ed.) ISWC 2016. LNCS, vol. 9981, pp. 498–514. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46523-4_30CrossRefGoogle Scholar
  10. 10.
    Saul, L.K., Roweis, S.T.: Think globally, fit locally: unsupervised learning of low dimensional manifolds. JMLR 4(Jun), 119–155 (2003)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Shi, B., Weninger, T.: Open-world knowledge graph completion. CoRR abs/1711.03438 (2017)Google Scholar
  12. 12.
    Tang, D., Qin, B., Liu, T.: Document modeling with gated recurrent neural network for sentiment classification. In: EMNLP, pp. 1422–1432. ACL (2015)Google Scholar
  13. 13.
    Thoma, S., Rettinger, A., Both, F.: Towards holistic concept representations: embedding relational knowledge, visual attributes, and distributional word semantics. In: d’Amato, C., et al. (eds.) ISWC 2017. LNCS, vol. 10587, pp. 694–710. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68288-4_41CrossRefGoogle Scholar
  14. 14.
    Toutanova, K., Chen, D., Pantel, P., Poon, H., Choudhury, P., Gamon, M.: Representing text for joint embedding of text and knowledge bases. In: EMNLP, pp. 1499–1509. ACL (2015)Google Scholar
  15. 15.
    Trouillon, T., Welbl, J., Riedel, S., Gaussier, E., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, JMLR Workshop and Conference Proceedings, vol. 48, pp. 2071–2080. JMLR.org (2016)Google Scholar
  16. 16.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph and text jointly embedding. In: EMNLP, pp. 1591–1601. ACL (2014)Google Scholar
  17. 17.
    Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: AAAI, pp. 1112–1119. AAAI Press (2014)Google Scholar
  18. 18.
    Xie, R., Liu, Z., Jia, J., Luan, H., Sun, M.: Representation learning of knowledge graphs with entity descriptions. In: AAAI, pp. 2659–2665. AAAI Press (2016)Google Scholar
  19. 19.
    Yamada, I., Shindo, H., Takeda, H., Takefuji, Y.: Joint learning of the embedding of words and entities for named entity disambiguation. In: CoNLL, pp. 250–259. ACL (2016)Google Scholar
  20. 20.
    Yin, W., Schütze, H.: Learning word meta-embeddings. In: ACL, vol. 1. ACL (2016)Google Scholar
  21. 21.
    Zhong, H., Zhang, J., Wang, Z., Wan, H., Chen, Z.: Aligning knowledge and text embeddings by entity descriptions. In: EMNLP, pp. 267–272. ACL (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of InformaticsUniversity of ZurichZurichSwitzerland
  2. 2.College of Computer Science and TechnologyZhejiang UniversityHangzhouChina
  3. 3.Alibaba-Zhejiang University Joint Institute of Frontier TechnologiesHangzhouChina

Personalised recommendations