EmbNum: Semantic Labeling for Numerical Values with Deep Metric Learning

  • Phuc NguyenEmail author
  • Khai Nguyen
  • Ryutaro Ichise
  • Hideaki Takeda
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11341)


Semantic labeling for numerical values is a task of assigning semantic labels to unknown numerical attributes. The semantic labels could be numerical properties in ontologies, instances in knowledge bases, or labeled data that are manually annotated by domain experts. In this paper, we refer to semantic labeling as a retrieval setting where the label of an unknown attribute is assigned by the label of the most relevant attribute in labeled data. One of the greatest challenges is that an unknown attribute rarely has the same set of values with the similar one in the labeled data. To overcome the issue, statistical interpretation of value distribution is taken into account. However, the existing studies assume a specific form of distribution. It is not appropriate in particular to apply open data where there is no knowledge of data in advance. To address these problems, we propose a neural numerical embedding model (EmbNum) to learn useful representation vectors for numerical attributes without prior assumptions on the distribution of data. Then, the “semantic similarities” between the attributes are measured on these representation vectors by the Euclidean distance. Our empirical experiments on City Data and Open Data show that EmbNum significantly outperforms state-of-the-art methods for the task of numerical attribute semantic labeling regarding effectiveness and efficiency.


Metric learning Semantic labeling Number embedding 


  1. 1.
    Adelfio, M.D., Samet, H.: Schema extraction for tabular data on the web. Proc. VLDB Endow. 6(6), 421–432 (2013)CrossRefGoogle Scholar
  2. 2.
    Ahmadov, A., Thiele, M., Eberius, J., Lehner, W., Wrembel, R.: Towards a hybrid imputation approach using web tables. In: 2015 IEEE/ACM 2nd International Symposium on Big Data Computing (BDC), pp. 21–30 (2015)Google Scholar
  3. 3.
    Bengio, Y., et al.: Learning deep architectures for AI. Found. Trends®. Mach. Learn. 2(1), 1–127 (2009)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678 (2016)
  5. 5.
    Dong, X., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 601–610. ACM (2014)Google Scholar
  6. 6.
    Ermilov, I., Auer, S., Stadler, C.: User-driven semantic mapping of tabular data. In: Proceedings of the 9th International Conference on Semantic Systems, pp. 105–112. ACM (2013)Google Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  8. 8.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
  9. 9.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, ICML 2015, vol. 37, pp. 448–456. (2015)Google Scholar
  10. 10.
    Lehmann, E.L., Romano, J.P.: Testing Statistical Hypotheses. Springer, Heidelberg (2006). Scholar
  11. 11.
    Lehmberg, O., Ritze, D., Meusel, R., Bizer, C.: A large public corpus of web tables containing time and context metadata. In: Proceedings of the 25th International Conference Companion on World Wide Web, pp. 75–76. International World Wide Web Conferences Steering Committee (2016)Google Scholar
  12. 12.
    Lehmberg, O., Ritze, D., Ristoski, P., Meusel, R., Paulheim, H., Bizer, C.: The mannheim search join engine. Web Semant.: Sci. Serv. Agents World Wide Web 35(P3), 159–166 (2015)CrossRefGoogle Scholar
  13. 13.
    Mitlöhner, J., Neumaier, S., Umbrich, J., Polleres, A.: Characteristics of open data CSV files. In: 2016 2nd International Conference on Open and Big Data (OBD), pp. 72–79 (2016)Google Scholar
  14. 14.
    Nargesian, F., Zhu, E., Pu, K.Q., Miller, R.J.: Table union search on open data. Proc. VLDB Endow. 11(7), 813–825 (2018)CrossRefGoogle Scholar
  15. 15.
    Neumaier, S., Umbrich, J., Parreira, J.X., Polleres, A.: Multi-level semantic labelling of numerical values. In: Groth, P., et al. (eds.) ISWC 2016 Part I. LNCS, vol. 9981, pp. 428–445. Springer, Cham (2016). Scholar
  16. 16.
    Nguyen, T.T., Nguyen, Q.V.H., Weidlich, M., Aberer, K.: Result selection and summarization for web table search. In: 2015 IEEE 31st International Conference on Data Engineering (ICDE), pp. 231–242. IEEE (2015)Google Scholar
  17. 17.
    Pham, M., Alse, S., Knoblock, C.A., Szekely, P.: Semantic labeling: a domain-independent approach. In: Groth, P., et al. (eds.) ISWC 2016 Part I. LNCS, vol. 9981, pp. 446–462. Springer, Cham (2016). Scholar
  18. 18.
    Ramnandan, S.K., Mittal, A., Knoblock, C.A., Szekely, P.: Assigning semantic labels to data sources. In: Gandon, F., Sabou, M., Sack, H., d’Amato, C., Cudré-Mauroux, P., Zimmermann, A. (eds.) ESWC 2015. LNCS, vol. 9088, pp. 403–417. Springer, Cham (2015). Scholar
  19. 19.
    Ritze, D., Lehmberg, O., Bizer, C.: Matching html tables to DBpedia. In: Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics, p. 10. ACM (2015)Google Scholar
  20. 20.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)Google Scholar
  21. 21.
    Sekhavat, Y.A., Di Paolo, F., Barbosa, D., Merialdo, P.: Knowledge base augmentation using tabular data. In: LDOW (2014)Google Scholar
  22. 22.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations (ICLR2014), CBLS, April 2014 (2014)Google Scholar
  23. 23.
    Sharif Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806–813 (2014)Google Scholar
  24. 24.
    Stonebraker, M., et al.: Data curation at scale: the data tamer system. In: CIDR (2013)Google Scholar
  25. 25.
    van der Maaten, L., Hinton, G.: Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)zbMATHGoogle Scholar
  26. 26.
    Venetis, P., et al.: Recovering semantics of tables on the web. Proc. VLDB Endow. 4(9), 528–538 (2011)CrossRefGoogle Scholar
  27. 27.
    Wang, J., Wang, H., Wang, Z., Zhu, K.Q.: Understanding tables on the web. In: Atzeni, P., Cheung, D., Ram, S. (eds.) ER 2012. LNCS, vol. 7532, pp. 141–155. Springer, Heidelberg (2012). Scholar
  28. 28.
    Wikipedia contributors: Inverse transform sampling—Wikipedia, the free encyclopedia (2018). Accessed 3 July 2018Google Scholar
  29. 29.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014 Part I. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). Scholar
  30. 30.
    Zhang, M., Chakrabarti, K.: Infogather+: semantic matching and annotation of numeric and time-varying attributes in web tables. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, pp. 145–156. ACM (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Phuc Nguyen
    • 1
    • 2
    Email author
  • Khai Nguyen
    • 2
  • Ryutaro Ichise
    • 1
    • 2
  • Hideaki Takeda
    • 1
    • 2
  1. 1.SOKENDAI (The Graduate University for Advanced Studies)HayamaJapan
  2. 2.National Institute of InformaticsChiyoda-kuJapan

Personalised recommendations