Advertisement

Classification-Based Referring Expression Generation

  • Thiago Castro Ferreira
  • Ivandré Paraboni
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8403)

Abstract

This paper presents a study in the field of Natural Language Generation (NLG), focusing on the computational task of referring expression generation (REG). We describe a standard REG implementation based on the well-known Dale & Reiter Incremental algorithm, and a classification-based approach that combines the output of several support vector machines (SVMs) to generate definite descriptions from two publicly available corpora. Preliminary results suggest that the SVM approach generally outperforms incremental generation, which paves the way to further research on machine learning methods applied to the task.

Keywords

Natural Language Generation Referring Expressions Classification SVM 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dale, R., Reiter, E.: Computational interpretations of the Gricean maxims in the generation of referring expressions. Cognitive Science 19(2), 233–263 (1995)CrossRefGoogle Scholar
  2. 2.
    Krahmer, E., van Deemter, K.: Computational generation of referring expressions: A survey. Computational Linguistics 38(1), 173–218 (2012)CrossRefGoogle Scholar
  3. 3.
    Pereira, D.B., Paraboni, I.: A language modelling tool for statistical NLP. In: 5th Workshop on Information and Human Language Technology (TIL 2007), pp. 1679–1688. Anais do XXVII Congresso da SBC. Rio de Janeiro (2007)Google Scholar
  4. 4.
    Pereira, D.B., Paraboni, I.: Statistical surface realisation of portuguese referring expressions. In: Ranta, A., Nordström, B. (eds.) GoTAL 2008. LNCS (LNAI), vol. 5221, pp. 383–392. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    de Novais, E.M., Paraboni, I.: Portuguese text generation using factored language models. Journal of the Brazilian Computer Society 19(2), 135–146 (2013)CrossRefGoogle Scholar
  6. 6.
    Cuevas, R.R.M., Paraboni, I.: A machine learning approach to portuguese pronoun resolution. In: Geffner, H., Prada, R., Machado Alexandre, I., David, N. (eds.) IBERAMIA 2008. LNCS (LNAI), vol. 5290, pp. 262–271. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Belz, A., Gatt, A.: The attribute selection for GRE challenge: Overview and evaluation results. In: Proceedings of UCNLG+ MT: Language Generation and Machine Translation, Copenhagen, MT Summit XI, pp. 75–83 (2007)Google Scholar
  8. 8.
    Krahmer, E., van Erk, S., Verleg, A.: Graph-based generation of referring expressions. Computational Linguistics 29(1), 53–72 (2003)CrossRefzbMATHGoogle Scholar
  9. 9.
    de Lucena, D.J., Pereira, D.B., Paraboni, I.: From semantic properties to surface text: The generation of domain object descriptions. Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial 14(45), 48–58 (2010)Google Scholar
  10. 10.
    van Deemter, K., van der Sluis, I., Gatt, A.: Building a semantically transparent corpus for the generation of referring expressions. In: Proceedings of the Fourth International Natural Language Generation Conference, INLG 2006, pp. 130–132. Association for Computational Linguistics, Stroudsburg (2006)CrossRefGoogle Scholar
  11. 11.
    Viethen, J., Dale, R.: The use of spatial relations in referring expression generation. In: Proceedings of the Fifth International Natural Language Generation Conference, INLG 2008, pp. 59–67. Association for Computational Linguistics, Stroudsburg (2008)CrossRefGoogle Scholar
  12. 12.
    Viethen, J., Dale, R.: GRE3D7: A corpus of distinguishing descriptions for objects in visual scenes. In: Proceedings of the UCNLG+Eval: Language Generation and Evaluation Workshop, pp. 12–22. Association for Computational Linguistics, Edinburgh (2011)Google Scholar
  13. 13.
    Gatt, A., Belz, A., Kow, E.: The TUNA challenge 2008: overview and evaluation results. In: Proceedings of the Fifth International Natural Language Generation Conference, INLG 2008, pp. 198–206. Association for Computational Linguistics, Stroudsburg (2008)CrossRefGoogle Scholar
  14. 14.
    Gatt, A., Belz, A., Kow, E.: The TUNA-REG challenge 2009: Overview and evaluation results. In: Proceedings of the 12th European Workshop on Natural Language Generation, ENLG 2009, pp. 174–182. Association for Computational Linguistics, Stroudsburg (2009)CrossRefGoogle Scholar
  15. 15.
    Jordan, P.W., Walker, M.A.: Learning content selection rules for generating object descriptions in dialogue. J. Artif. Int. Res. 24(1), 157–194 (2005)zbMATHGoogle Scholar
  16. 16.
    Viethen, J., Dale, R.: Speaker-dependent variation in content selection for referring expression generation. In: Proceedings of the Australasian Language Technology Association Workshop 2010, Melbourne, Australia, pp. 81–89 (December 2010)Google Scholar
  17. 17.
    Viethen, J.: The Generation of Natural Descriptions: Corpus-Based Investigations of Referring Expressions in Visual Domains. PhD thesis, Macquarie University, Sydney, Australia (2011)Google Scholar
  18. 18.
    Grice, H.P.: Logic and conversation. In: Cole, P., Morgan, J.L. (eds.) Syntax and Semantics, vol. 3, Academic Press, New York (1975)Google Scholar
  19. 19.
    Dale, R., Haddock, N.: Generating referring expressions involving relations. In: Proceedings of the Fifth Conference on European Chapter of the Association for Computational Linguistics, EACL 1991, pp. 161–166. Association for Computational Linguistics, Stroudsburg (1991)Google Scholar
  20. 20.
    Paraboni, I.: An algorithm for generating document-deictic references. In: Procs. of Workshop Coherence in Generated Multimedia, Associated with First Int. Conf. on Natural Language Generation (INLG 2000), Mitzpe Ramon, pp. 27–31 (2000)Google Scholar
  21. 21.
    Krahmer, E., Theune, M.: Efficient context-sensitive generation of referring expressions. In: Information Sharing: Reference and Presupposition in Language Generation and Interpretation, vol. 143, pp. 223–263. CSLI Publications, California (2002)Google Scholar
  22. 22.
    Kelleher, J.D., Kruijff, G.J.M.: Incremental generation of spatial referring expressions in situated dialog. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, ACL-44, pp. 1041–1048. Association for Computational Linguistics, Stroudsburg (2006)Google Scholar
  23. 23.
    Eugenio, B.D., Jordan, P.W., Thomason, R.H., Moore, J.D.: The agreement process: An empirical investigation of human–human computer-mediated collaborative dialogs. International Journal of Human-Computer Studies 53(6), 1017–1076 (2000)CrossRefzbMATHGoogle Scholar
  24. 24.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, 2825–2830 (2011)zbMATHGoogle Scholar
  25. 25.
    Knerr, S., Personnaz, L., Dreyfus, G.: Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: Soulié, F., Hérault, J. (eds.) Neurocomputing. NATO ASI Series, vol. 68, pp. 41–50. Springer, Heidelberg (1990)CrossRefGoogle Scholar
  26. 26.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  27. 27.
    Passonneau, R.: Measuring agreement on set-valued items (MASI) for semantic and pragmatic annotation. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC), Valletta, Malta, pp. 831–836 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Thiago Castro Ferreira
    • 1
  • Ivandré Paraboni
    • 1
  1. 1.School of Arts, Sciences and HumanitiesUniversity of São Paulo (USP / EACH)São PauloBrazil

Personalised recommendations