Experiments on Building Language Resources for Multi-Modal Dialogue Systems
Abstract
The paper presents the experiments made to adapt and to synchronise the linguistic resources of the French language processing modules integrated in the MIAMM prototype, designed to handle multi-modal human-machine interactions. These experiments allowed us to identify a methodology for adapting multilingual resources for a dialogue system. In the paper, we describe the iterative joint process used to build linguistic resources for the two cooperative modules: speech recognition for speech modality and syntactic/semantic parsing.
Fichier principal
LREC-611.pdf (161.23 Ko)
Télécharger le fichier
lrec2004_4.ppt (3.78 Mo)
Télécharger le fichier
Origin | Files produced by the author(s) |
---|
Format | Other |
---|
Loading...