The Philips automatic train timetable information system
Speech Communication - Special issue on interactive voice technology for telecommunication applications
The LIMSI RailTel system: field trial of a telephone service for rail travel information
Speech Communication - Special issue on interactive voice technology for telecommunication applications (IVITA '96)
Speech Communication - Special issue on interactive voice technology for telecommunication applications
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
A connectionist model of sentence comprehension and production
A connectionist model of sentence comprehension and production
Hi-index | 0.00 |
A contribution to the understanding module of a domain-specific dialogue system is presented in this work. The task consists of answering telephone queries about train timetables, prices and services for long distance trains in Spanish. In this system, the representation of the meaning of the user utterances is made by means of frames, which determine the type of communication of the user turn, and by their associated cases, which supply the data of the utterance.We focus on the classification of a user turn given in natural language in a specific class of frame. We used multilayer perceptrons to classify a user turn as belonging to a frame class. This classification can help in the posterior processes of understanding and dialogue management.