Uniclass and Multiclass Connectionist Classification of Dialogue Acts

  • María José Castro
  • David Vilar
  • Emilio Sanchis
  • Pablo Aibar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)

Abstract

Classification problems are traditionally focused on uniclass samples, that is, each sample of the training and test sets has one unique label, which is the target of the classification. In many real life applications, however, this is only a rough simplification and one must consider some techniques for the more general multiclass classification problem, where each sample can have more than one label, as it happens in our task. In the understanding module of a domain-specific dialogue system for answering telephone queries about train information in Spanish which we are developing, a user turn can belong to more than one type of frame. In this paper, we discuss general approaches to the multiclass classification problem and show how these techniques can be applied by using connectionist classifiers. Experimentation with the data of the dialogue system shows the inherent difficulty of the problem and the effectiveness of the different methods are compared.

References

  1. 1.
    Castro, M.J., Sanchis, E.: A Simple Connectionist Approach to Language Understanding in a Dialogue System. In: Advances in Artificial Intelligence, pp. 664–673. Springer, Heidelberg (2002)Google Scholar
  2. 2.
    Sanchis, E., Castro, M.J.: Dialogue Act Connectionist Detection in a Spoken Dialogue System. In: Soft Computing Systems. Design, Management and Applications, pp. 644–651. IOS Press, Amsterdam (2002)Google Scholar
  3. 3.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: PDP: Computational models of cognition and perception, I, pp. 319–362. MIT Press, Cambridge (1986)Google Scholar
  4. 4.
    McCallum, A.K.: Multi-Label Text Classification with a Mixture Model Trained by EM. In: Proc. NIPS 1999 (1999)Google Scholar
  5. 5.
    Schapire, R.E., Singer, Y.: Boostexter: A boosting-based system for text categorization. Machine Learning 39(2/3), 135–168 (2000)MATHCrossRefGoogle Scholar
  6. 6.
    Yang, Y.: An evaluation of statistical approaches to text categorization. Information Retrieval 1(1/2), 69–90 (1999)CrossRefGoogle Scholar
  7. 7.
    Joachims, T.: Text categorization with Support Vector Machines: Learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137–142. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  8. 8.
    Nigam, K., et al.: Text classification from labeled and unlabeled documents using EM. Machine Learning 39(2/3), 103–134 (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Bonafonte, A., et al.: Desarrollo de un sistema de diálogo oral en dominios restringidos. In: Primeras Jornadas de Tecnología del Habla, Sevilla, Spain (2000)Google Scholar
  10. 10.
    Martínez, C., et al.: A Labelling Proposal to Annotate Dialogues. In: Proc. LREC 2002, Las Palmas de Gran Canaria, Spain, vol. V, pp. 1577–1582 (2002)Google Scholar
  11. 11.
    Stolcke, A., et al.: Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech. Computational Linguistics 26(3), 339–373 (2000)CrossRefGoogle Scholar
  12. 12.
    Zell, A., et al.: SNNS: Stuttgart Neural Network Simulator. User Manual, Version 4.2. Univ. of Stuttgart, Germany (1998)Google Scholar
  13. 13.
    Bishop, C.M.: Neural networks for pattern recognition. Oxford Univ. Press, Oxford (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • María José Castro
    • 1
  • David Vilar
    • 1
  • Emilio Sanchis
    • 1
  • Pablo Aibar
    • 2
  1. 1.Departament de Sistemes Informàtics i ComputacióUniversitat Politècnica de ValènciaValènciaSpain
  2. 2.Departament de Llenguatges i Sistemes InformàticsUniversitat Jaume I de CastellóCastellóSpain

Personalised recommendations