Advertisement

Towards Spatial Word Embeddings

  • Paul MoussetEmail author
  • Yoann Pitarch
  • Lynda Tamine
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11438)

Abstract

Leveraging textual and spatial data provided in spatio-textual objects (eg., tweets), has become increasingly important in real-world applications, favoured by the increasing rate of their availability these last decades (eg., through smartphones). In this paper, we propose a spatial retrofitting method of word embeddings that could reveal the localised similarity of word pairs as well as the diversity of their localised meanings. Experiments based on the semantic location prediction task show that our method achieves significant improvement over strong baselines.

Keywords

Word embeddings Retrofitting Spatial 

Notes

Acknowledgments

This research was supported by IRIT and ATOS Intégration research program under ANRT CIFRE grant agreement \(\#2016/403\).

References

  1. 1.
    Cheng, J., Wang, Z., Wen, J.R., Yan, J., Chen, Z.: Contextual text understanding in distributional semantic space. In: Proceedings of CIKM 2015, pp. 133–142 (2015)Google Scholar
  2. 2.
    Craswell, N.: Mean reciprocal rank. In: Liu, L., Özsu, M.T. (eds.) Encyclopedia of Database Systems, p. 1703. Springer, Boston (2009).  https://doi.org/10.1007/978-0-387-39940-9CrossRefGoogle Scholar
  3. 3.
    Dalvi, N., Kumar, R., Pang, B., Tomkins, A.: A translation model for matching reviews to objects. In: Proceedings of CIKM 2009, pp. 167–176 (2009)Google Scholar
  4. 4.
    De Smith, M., Goodchild, M.F.: Geospatial Analysis: A Comprehensive Guide to Principles, Techniques and Software Tools. Metador (2007)Google Scholar
  5. 5.
    Deveaud, R., Albakour, M.D., Macdonald, C., Ounis, I.: Experiments with a venue-centric model for personalised and time-aware venue suggestion. In: Proceedings of CIKM 2015, pp. 53–62 (2015)Google Scholar
  6. 6.
    Fang, Y., Chang, M.W.: Entity linking on microblogs with spatial and temporal signals. Trans. Assoc. Comput. Linguist. 2, 259–272 (2014)CrossRefGoogle Scholar
  7. 7.
    Faruqui, M., Dodge, J., Jauhar, S.K., Dyer, C., Hovy, E., Smith, N.A.: Retrofitting word vectors to semantic lexicons. In: Proceedings of NAACL 2015, pp. 1606–1615 (2015)Google Scholar
  8. 8.
    Glavaš, G., Vulić, I.: Explicit retrofitting of distributional word vectors. In: Proceedings of ACL 2018, pp. 34–45 (2018)Google Scholar
  9. 9.
    Han, J., Sun, A., Cong, G., Zhao, W.X., Ji, Z., Phan, M.C.: Linking fine-grained locations in user comments. Trans. Knowl. Data Eng. 30(1), 59–72 (2018)CrossRefGoogle Scholar
  10. 10.
    Iacobacci, I., Pilehvar, M.T., Navigli, R.: SensEmbed: learning sense embeddings for word and relational similarity. In: Proceedings of ACL and IJCNLP 2017, pp. 95–105 (2017)Google Scholar
  11. 11.
    Imran, M., Castillo, C., Diaz, F., Vieweg, S.: Processing social media messages in mass emergency: a survey. ACM Comput. Surv. 47(4), 67:1–67:38 (2015)CrossRefGoogle Scholar
  12. 12.
    MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of BSMSP 1967, pp. 281–297 (1967)Google Scholar
  13. 13.
    Mancini, M., Camacho-Collados, J., Iacobacci, I., Navigli, R.: Embedding words and senses together via joint knowledge-enhanced training. In: Proceedings of CoNLL 2017, pp. 100–111 (2017)Google Scholar
  14. 14.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS 2013, pp. 3111–3119 (2013)Google Scholar
  15. 15.
    Mrkšić, N., et al.: Counter-fitting word vectors to linguistic constraints. arXiv preprint (2016)Google Scholar
  16. 16.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of EMNLP 2014, pp. 1532–1543 (2014)Google Scholar
  17. 17.
    Powers, D.M.: Evaluation: from precision, recall and f-measure to ROC, informedness, markedness & correlation. J. Mach. Learn. Technol. 2, 37–63 (2011)Google Scholar
  18. 18.
    Robertson, S.E., Jones, K.S.: Relevance weighting of search terms. J. Am. Soc. Inf. Sci. 27(3), 129–146 (1976)CrossRefGoogle Scholar
  19. 19.
    Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65 (1987)CrossRefGoogle Scholar
  20. 20.
    Vulić, I., Mrkšić, N.: Specialising word vectors for lexical entailment. In: Proceedings of NAACL-HLT 2018, pp. 1134–1145 (2018)Google Scholar
  21. 21.
    Xu, C., et al.: RC-NET: a general framework for incorporating knowledge into word representations. In: Proceedings of CIKM 2014, pp. 1219–1228 (2014)Google Scholar
  22. 22.
    Yu, M., Dredze, M.: Improving lexical embeddings with semantic knowledge. In: Proceedings of ACL 2014, pp. 545–550 (2014)Google Scholar
  23. 23.
    Zamani, H., Croft, W.B.: Estimating embedding vectors for queries. In: Proceedings of ICTIR 2016, pp. 123–132 (2016)Google Scholar
  24. 24.
    Zhang, D., Chan, C.Y., Tan, K.L.: Processing spatial keyword query as a top-k aggregation query. In: Proceedings of SIGIR 2014, pp. 355–364 (2014)Google Scholar
  25. 25.
    Zhao, K., Cong, G., Sun, A.: Annotating points of interest with geo-tagged tweets. In: Proceedings of CIKM 2016, pp. 417–426 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.IRIT, Université de Toulouse, CNRSToulouseFrance
  2. 2.Atos IntégrationToulouseFrance

Personalised recommendations