Title :
MeteoBayes: Effective Plan Recognition in a Weather Dialogue System
Author :
Maragoudakis, Manolis ; Thanopoulos, Aristomenis ; Fakotakis, Nikos
Author_Institution :
Patras Univ.
Abstract :
When you´ve called a voice portal for any kind of information retrieval, chances are that an automated system guided the entire interaction. It might have correctly identified your goal, but probably only after asking too many questions. MeteoBayes is a meteorological information dialogue system that lets you use natural language to direct the interaction. Based on Bayesian networks, MeteoBayes´ inference engine attempts to identify user intentions by consulting its past dialogue repository. For unfamiliar words, MeteoBayes has an unknown-term disambiguation module that learns word similarities from texts to avoid unnecessary system inquiries, thus speeding up the understanding process
Keywords :
belief networks; geophysics computing; inference mechanisms; information retrieval; meteorology; natural language processing; Bayesian networks; MeteoBayes meteorological information dialogue system; dialogue manager; domain knowledge; effective plan recognition; inference engine; information retrieval; knowledge acquisition; multilevel linguistic processing; natural language; semantic representation; unknown-term disambiguation module; weather dialogue system; word similarities; Automatic speech recognition; Bayesian methods; Engines; Information retrieval; Meteorology; Mobile handsets; Motion pictures; Natural languages; Portals; Stock markets; Bayesian Networks; information retrieval; natural language processing; plan recognition; user modeling;
Journal_Title :
Intelligent Systems, IEEE
DOI :
10.1109/MIS.2007.14
