The Community for Technology Leaders
Green Image
Issue No. 01 - January/February (2007 vol. 22)
ISSN: 1541-1672
pp: 67-77
Manolis Maragoudakis , University of Patras
Aristomenis Thanopoulos , University of Patras
Nikos Fakotakis , University of Patras
When you've called a voice portal for any kind of information retrieval, chances are that an automated system guided the entire interaction. Perhaps it correctly identified your goal, but only after too many questions. MeteoBayes, a meteorological information dialogue system, lets users employ natural language to clarify their goals. MeteoBayes uses a Bayesian networks-based inference engine to establish user intentions by consulting its past dialogue repository. Because unknown terms are likely to come up, MeteoBayes's unknown term disambiguation module learns word similarities from texts to avoid unnecessary system inquiries, thus speeding up the understanding process.
information retrieval, Bayesian Networks, natural language processing, user modeling, plan recognition

N. Fakotakis, A. Thanopoulos and M. Maragoudakis, "MeteoBayes: Effective Plan Recognition in a Weather Dialogue System," in IEEE Intelligent Systems, vol. 22, no. , pp. 67-77, 2007.
90 ms
(Ver 3.3 (11022016))