Abstract
Conversational agents interact with users using natural language interface. Especially in Internet space, their role has been recently highlighted as a virtual representative of a web site. However, most of them use simple pattern matching techniques without considering user’s goal. In this paper, we propose a conversational agent that utilizes user model constructed on Bayesian network for the responses consistent with user’s goal. The agent is applied to the active guide of a website, which shows that the user modeling based on Bayesian network helps to respond to user’s queries appropriately with the their goals.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. Weizenbaun: ELIZA-a Computer Program for the Study of Natural Language Communication between Man and Machine. Communications of the ACM 9(1). (1965) 36–45
D. Pynadath and M. Wellman: Accounting for Context in Plan Recognition with Application to Traffic Monitoring. Proc. of the Eleventh Conf. on Uncertainty in Artificial Intelligence. (1995) 472–481
D. Albrecht et al:Towards a Bayesian Model forKeyhole Plan Recognition in Large Domains. Proc. of the Sixth Int. Conf. on User Modeling. (1997) 365–376.
E. Horvitz and T. Paek: A Computational Architecture for Conversation. Proc. of the Seventh Int. Conf. on User Modeling. (1999) 201–210
F.V. Jensen: An Introduction to Bayesian Networks, Springer-Verlag. (1996)
N. Friedman et al: Using Bayesian Networks to Analyze Expression Data. Proc. of the Fourth Annual Int. Conf. on Computational Molecular Biology. (2000) 127–135
J.F. Allen: Mixed-Initiative Interaction. IEEE Intelligent Systems 5 (1999) 14–16
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, SI., Sung, C., Cho, SB. (2001). An Effective Conversational Agent with User Modeling Based on Bayesian Network. In: Zhong, N., Yao, Y., Liu, J., Ohsuga, S. (eds) Web Intelligence: Research and Development. WI 2001. Lecture Notes in Computer Science(), vol 2198. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45490-X_54
Download citation
DOI: https://doi.org/10.1007/3-540-45490-X_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42730-8
Online ISBN: 978-3-540-45490-8
eBook Packages: Springer Book Archive