Efficient Domain Action Classification Using Neural Networks

  • Hyunjung Lee
  • Harksoo Kim
  • Jungyun Seo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


Speaker’s intentions can be represented into domain actions (domain-independent speech acts and domain-dependent concept sequences). Therefore, domain action classification is very useful to a dialogue system that should catch user’s intention in order to generate correct reaction. In this paper, we propose a neural network model to determine speech acts and concept sequences at the same time. To avoid biased learning problems, the proposed model uses low-level linguistic features and filters out uninformative features using χ 2 statistic. In the experiment, the proposed model showed better performances than the previous work in speech act classification. Moreover, the proposed model showed meaningful results when the size of training corpus was small. Based on the experimental results, we believe that the proposed model will be more helpful to dialogue systems because it manages speech act classification and concept sequence classification at the same time. We also believe that the proposed model can alleviate sparse data problems in speech act classification.


Domain Action Input Feature Training Corpus Dialogue System Lexical Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Allen, J.: Natural Language Understanding. The Benjamin/Cummings Publishing Company, Inc. (1987)Google Scholar
  2. 2.
    Caberry, S.: A Pragmatics-based Approach to Ellipsis Resolution. Computational Linguistics 15(2), 75–96 (1989)Google Scholar
  3. 3.
    Kim, K., Kim, H., Seo, J.: A Neural Network Model with Feature Selection for Korean Speech Act Classification. International Journal of Neural Systems 14(6), 407–414 (2004)CrossRefGoogle Scholar
  4. 4.
    Lambert, L., Caberry, S.: A Tripartite Plan-based Model of Dialogue. In: Proceedings of ACL, pp. 47–54 (1991)Google Scholar
  5. 5.
    Langley, C.: Analysis for Speech Translation Using Grammar-based Parsing and Automatic Classification. In: Proceedings of the ACL Student Research Workshop (2002)Google Scholar
  6. 6.
    Lee, S., Seo, J.: An Analysis of Korean Speech Act Using Hidden Markov Model with Decision Trees. In: Proceedings of ICPOL, pp. 397–400 (2001)Google Scholar
  7. 7.
    Levin, L., Langley, C., Lavie, A., Gates, D., Wallace, D., Peterson, K.: Domain Specific Speech Acts for Spoken Language Translation. In: Proceedings of 4th SIGdial Workshop on Discourse and Dialogue (2003)Google Scholar
  8. 8.
    Litman, D.J., Allen, J.F.: A Plan Recognition Model for Subdialogues in Conversations. Cognitive Science 11, 163–200 (1987)CrossRefGoogle Scholar
  9. 9.
    Lweis, D.D., Ringuette, M.: Comparison of Two Learning Algorithms for Text Categorization. In: Proceedings of SDAIR (1994)Google Scholar
  10. 10.
    Samuel, K., Caberry, S., Vijay-Shanker, K.: Computing Dialogue Acts from Features with Transform-based Learning. In: Proceedings of the AAAI Spring Symposium, pp. 90–97 (1998)Google Scholar
  11. 11.
    Schűtze, H., Hull, D.A., Pedersen, J.O.: A Comparison of Classifiers and Document Representations for the Routing Problem. In: Proceedings of SIGIR (1995)Google Scholar
  12. 12.
    Stolcke, A., Ries, K., Coccaro, N., Shiriberg, E., Bates, R., Jurafsky, D., Taylor, P., Van Ess-Dykema, C., Martin, R., Meteer, M.: Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech. Computational Linguistics 26(3), 339–373 (2000)CrossRefGoogle Scholar
  13. 13.
    Wiener, E., Pedersen, J.O., Weigend, A.S.: A Neural Network Approach to Topic Spotting. In: Proceedings of SDAIR (1995)Google Scholar
  14. 14.
    Yang, Y., Pedersen, J.O.: A Comparative Study on Feature Selection in Text Categorization. In: Proceedings of the 14th International Conference on Machine Learning (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hyunjung Lee
    • 1
  • Harksoo Kim
    • 2
  • Jungyun Seo
    • 3
  1. 1.Natural Language Processing Lab., Department of Computer ScienceSogang UniversitySeoulRepublic of Korea
  2. 2.Program of Computer and Communications Engineering, College of Information TechnologyKangwon National UniversityKangwon-doRepublic of Korea
  3. 3.Department of Computer Science and Interdisciplinary Program of Integrated BiotechnologySogang UniversitySeoulRepublic of Korea

Personalised recommendations