Asking the Right Questions: Task Hierarchy Predictive Traversal Mechanisms for Mixed Initiative Dialog Management

Juan M. Huerta

Abstract

This paper describes an approach for building conversational applications that dynamically adjust to the user’s level of expertise based on the user’s responses. In our method, the Dialog Manager interacts with the application user through a mechanism that adjusts the prompts presented to the user based on a hierarchical model of the domain, the recent interaction history, and the known complexity of the domain itself. The goal is to present a conversational modality for experienced or confident users, and a simpler Directed Dialog experience for the more inexperienced users, and to dynamically identify these levels of expertise from the user’s utterances. Our method uses a task hierarchy as a representation of the domain and follows a feedback control system framework to traverse of this tree. We illustrate these mechanisms with a simple sample domain based on a car rental application.

References

  1. AT&T “Need Help? Ask Allie ™” Web Application.
  2. Gorin, A. L., "Spoken dialog as a feedback control system," Proc. ESCA Workshop on spoken dialog systems, Visgo, Denmark, May 1995, pp. 173-176
  3. Gorin, A. L., Levinson, S. E. and Sankar, A., "An experiment in spoken language acquisition," IEEE Trans. Speech and Audio, vol. 2, no. 1, Part 2, Jan. 1994, pp. 224-240.
  4. Hochberg J. , Kambhatla N., Roukos Salim, “A Flexible Framework for Developing Mixed-Initiative Dialog Systems”, 3rd Sigdial Workshop on Discourse and Dialogue, 2002
  5. Huerta “Graph based representations and techniques for NLU Application Development” Proc. ICASSP 2003, Honk Kong.
  6. Louwerse, M. Graesser A. Olney A. “Good Computational Manners”, AAAI Symposium Technical Report, November 15-17, 2002, North Falmouth, Massachusetts
  7. A.L. Gorin, G. Riccardi and J.H. Wright How May I Help you Speech Communication, vol. 23, pp. 113-127, 1997
  8. W3C, VXML 2.0 http://www.w3.org/TR/voicexml20/
  9. The MIT Galaxy System http://www.sls.csail.mit.edu/GALAXY.html
  10. Luo X., Papineni K, “IBM Darpa Communicator V 1.0”, Darpa Communicator Principal Investigators Meeting, Philadelphia USA 2000.
  11. Wright Jerry, Allen Gorin, Alicia Abella “Spoken Language Understanding within Dialogs Using a Graphical Model of Task Structure”, Proc. ICSLP, Sydney 1998.
  12. Meng, Wai and Pieraccinni, “The Use of Belief Networks for Mixed Initiative dialog Modeling” ICSLP 2000, Beijing China.
  13. Guzdial, M. Software-realized Scaffolding to Facilitate Programming for Science Learning. Interactive Learning Environments, Vol. 4, No. 1, 1995, 1-44.
  14. W3C, “XForms” http://www.w3.org/MarkUp/Forms/
Download


Paper Citation


in Harvard Style

M. Huerta J. (2004). Asking the Right Questions: Task Hierarchy Predictive Traversal Mechanisms for Mixed Initiative Dialog Management . In Proceedings of the 1st International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2004) ISBN 972-8865-05-8, pages 106-115. DOI: 10.5220/0002681301060115


in Bibtex Style

@conference{nlucs04,
author={Juan M. Huerta},
title={Asking the Right Questions: Task Hierarchy Predictive Traversal Mechanisms for Mixed Initiative Dialog Management},
booktitle={Proceedings of the 1st International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2004)},
year={2004},
pages={106-115},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002681301060115},
isbn={972-8865-05-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Natural Language Understanding and Cognitive Science - Volume 1: NLUCS, (ICEIS 2004)
TI - Asking the Right Questions: Task Hierarchy Predictive Traversal Mechanisms for Mixed Initiative Dialog Management
SN - 972-8865-05-8
AU - M. Huerta J.
PY - 2004
SP - 106
EP - 115
DO - 10.5220/0002681301060115