Advertisement

A Two-Stage Bayesian Network for Effective Development of Conversational Agent

  • Jin-Hyuk Hong
  • Sung-Bae Cho
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2690)

Abstract

Conversational agent is a system that provides user with proper information and maintains the context of dialogue based on natural language. When experts design the network for conversational agent of a domain, the network is usually very complicated and is hard to be understood. So the simplification of network by separating variables in the domain is helpful to design the conversational agent more efficiently. Composing Bayesian network as two stages, we aim to design conversational agent easily and analyze user’s query in detail. Also, by using previous information of dialogue, it is possible to maintain the context of conversation. Actually implementing it for a guide of web pages, we can confirm the usefulness of the proposed architecture for conversational agent.

Keywords

Bayesian Network Conversational Agent Active Conversation Sentence Pattern Previous Dialogue 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yang, Y., Chien, L., Lee, L.: Speaker intention modeling for large vocabulary mandarin spoken dialogues. In: Proc. of the 4th Int. Conf. on Spoken Language, pp. 713–716 (1996)Google Scholar
  2. 2.
    Allen, J., Byron, D., Dzikovska, M., Ferguson, G., Galescu, L., Stent, A.: Towards conversational human-computer interaction. AI Magazine 22(4), 27–37 (2001)Google Scholar
  3. 3.
    Chai, J., Horvath, V., Nicolov, N., Budzikowska, M., Kambhatla, N., Zadrozny, W.: Natural language sales assistant: A web-based dialog system for online sales. In: Proc. Of the 13th Annual Conf. on Innovative Applications of Artificial Intelligence, pp.19–26 (2001)Google Scholar
  4. 4.
    Horvitz, E., Breese, J., Heckerman, D., Hovel, D., Rommelse, K.: The lumiere project: Bayesian user modeling for inferring the goals and needs of software users. In: Proc. of the 14th Conf. Uncertainty in Artificial Intelligence, pp. 256–265 (1998)Google Scholar
  5. 5.
    Albrecht, D., Zukerman, I., Nicholcon, A., Bud, A.: Towards a Bayesian model for keyhole plan recognition in large domains. In: Proc. of the 6th Int. Conf. on User Modeling, pp. 365–376 (1997)Google Scholar
  6. 6.
    Lee, S.-I., Sung, C., Cho, S.-B.: An effective conversational agent with user modeling based on Bayesian network. In: Zhong, N., Yao, Y., Ohsuga, S., Liu, J. (eds.) WI 2001. LNCS (LNAI), vol. 2198, pp. 428–432. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  7. 7.
    Macskassy, S., Stevenson, S.: A conversational agent. In: Master Essay, Rutgers University (1996)Google Scholar
  8. 8.
    Heckerman, D., Horvitz, E.: Inferring informational goals from free-text queries: A Bayesian approach. In: Proc. of the 14th Conf. on Uncertainty in Artificial Intelligence, pp.230–237 (1998)Google Scholar
  9. 9.
    Ferguson, G., Allen, J., Miller, B.: TRAINS-95: Towards a mixed-initiative planning assistant. In: Proc. of the 3rd Conf. on Artificial Intelligence Planning Systems, pp.70–77 (1996)Google Scholar
  10. 10.
    Paek, T., Horvitz, E.: Conversation as action under uncertainty. In: Proc. of the 16th Conf. on Uncertainty in Artificial Intelligence, pp. 455–464 (2000)Google Scholar
  11. 11.
    Charniak, E.: Bayesian networks without tears. AI Magazine 12(4), 50–63 (1991)Google Scholar
  12. 12.
    Stephenson, T.: An introduction to Bayesian network theory and usage. IDIAP-RR00- 03 (2000)Google Scholar
  13. 13.
    Horvitz, E., Paek, T.: A computational architecture for conversation. In: Proc. of the 7th Int. Conf. on User Modeling, pp. 201–210 (1999)Google Scholar
  14. 14.
    Allen, J., Ferguson, G., Stent, A.: An architecture for more realistic conversational systems. In: Proc. of Intelligent User Interfaces, pp. 1–8 (2001)Google Scholar
  15. 15.
    Allen, J.: Mixed Initiative Interaction. IEEE Intelligent Systems 14(6), 14–23 (1999)Google Scholar
  16. 16.
    Wu, X., Zheng, F., Xu, M.: TOPIC Forest: A plan-based dialog management structure. In: Conf. on Acoustics, Speech and Signal Processing, pp.617–620 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jin-Hyuk Hong
    • 1
  • Sung-Bae Cho
    • 1
  1. 1.Dept. of Computer ScienceYonsei UniversitySeoulKorea

Personalised recommendations