A Statistical User Simulation Technique for the Improvement of a Spoken Dialog System

  • Lluís F. Hurtado
  • David Griol
  • Emilio Sanchis
  • Encarna Segarra
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

In this paper, we present a statistical approach for the automatic generation of dialogs by means of a user simulator. This technique can be used to generate dialogs with reduced effort, facilitating the evaluation and improvement of spoken dialog systems. In our approach for user simulation, the user answer is selected taking into account the history of the dialog and the last system turn, as well as the objective(s) set for the dialog. The user model is automatically learned from a training corpus that is labeled in terms of dialog acts. This methodology has been evaluated within the framework of the DIHANA project, whose goal is the design and development of a dialog system to access a railway information system using spontaneous speech in Spanish.

Keywords

spoken dialog systems user simulation dialog management dialog system evaluation 

References

  1. 1.
    Seneff, S., Polifroni, J.: Dialogue management in the Mercury flight reservation system. In: Proc. ANLP-NAACL 2000, Satellite Workshop pp. 1–6 (2000)Google Scholar
  2. 2.
    Lamel, L., Rosset, S., Gauvain, J., Bennacef, S., Garnier-Rizet, M., Prouts, B.: The LIMSI ARISE System. Speech Communication 4(31), 339–353 (2000)CrossRefGoogle Scholar
  3. 3.
    Rudnicky, A., Thayer, E., Constantinides, P., Tchou, C., Shern, R., Lenzo, K., Xu, W., Oh, A.: Creating natural dialogs in the Carnegie Mellon Communicator system. Proceedings of Eurospeech 1(4), 1531–1534 (1999)Google Scholar
  4. 4.
    Ward, W., Pellom, B.: The CU Communicator system. In: Proc. of ASRU-IEEE Workshop, Keystone, Colorado (USA) (1999)Google Scholar
  5. 5.
    Bohus, D., Grau, S., Huggins-Daines, D., Keri, V., Krishna, G., Kumar, R., Raux, A., Tomko, S.: Conquest - an open-source dialog system for conferences. In: Proc. HLT-NAACL 2007, Rochester, NY (2007)Google Scholar
  6. 6.
    Litman, D., Singh, S., Kearns, M., Walker, M.: Njfun: a reinforcement learning spoken dialogue system. In: Proceedings of the ANLP/NAACL 2000 Workshop on Conversational Systems, Seattle, USA, Association for Computational Linguistics pp. 17–20 (2000)Google Scholar
  7. 7.
    Zue, V., Seneff, S., Glass, J., Polifroni, J., Pao, C., Hazen, T., Hetherington, L.: Jupiter: A telephone-based conversational interface for weather information. IEEE Trans. on Speech and Audio Proc. 8(1), 85–96 (2000)CrossRefGoogle Scholar
  8. 8.
    Georgila, K., Henderson, J., Lemon, O.: User Simulation for Spoken Dialogue Systems: Learning and Evaluation. In: Proc. of Interspeech 2006-ICSLP, Pittsburgh, pp. 1065–1068 (2006)Google Scholar
  9. 9.
    Pietquin, O., Dutoit, T.: A probabilistic framework for dialog simulation and optimal strategy learning. IEEE Transactions on Speech and Audio Processing 14, 589–599 (2005)Google Scholar
  10. 10.
    Scheffler, K., Young, S.: Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning. In: Proc. Human Language Technology, San Diego, pp. 12–18 (2002)Google Scholar
  11. 11.
    Cuayáhuitl, H., Renals, S., Lemon, O., Shimodaira, H.: Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces. In: Proc. of InterSpeech’06-ICSLP, Pittsburgh, pp. 469–472 (2006)Google Scholar
  12. 12.
    Schatzmann, J., Weilhammer, K., Stuttle, M., Young, S.: A Survey of Statistical User Simulation Techniques for Reinforcement-Learning of Dialogue Management Strategies. Knowledge Engineering Review 21(2), 97–126 (2006)CrossRefGoogle Scholar
  13. 13.
    Griol, D., Hurtado, L., Segarra, E., Sanchis, E.: Managing unseen situations in a stochastic dialog model. In: Proc. of AAAI Workshop Stadistical and Empirical Approaches for Spoken Dialogue Systems, Boston, pp. 25–30 (2006)Google Scholar
  14. 14.
    Hurtado, L.F., Griol, D., Segarra, E., Sanchis, E.: A stochastic approach for dialog management based on neural networks. In: Proc. of Interspeech 2006-ICSLP, Pittsburgh, pp. 49–52 (2006)Google Scholar
  15. 15.
    Torres, F., Sanchis, E., Segarra, E.: Learning of stochastic dialog models through a dialog simulation technique. In: Proc. of Eurospeech 2005, Lisbon, pp. 817–820 (2005)Google Scholar
  16. 16.
    Griol, D., Torres, F., Hurtado, L., Grau, S., García, F., Sanchis, E., Segarra, E.: A dialog system for the DIHANA Project. In: Proc. of SPECOM 2006, S. Petersburgh (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Lluís F. Hurtado
    • 1
  • David Griol
    • 1
  • Emilio Sanchis
    • 1
  • Encarna Segarra
    • 1
  1. 1.Departament de Sistemes Informàtics i Computació (DSIC), Universitat Politècnica de València (UPV), Camí de Vera s/n, 46022 ValènciaSpain

Personalised recommendations