A Framework for Unsupervised Learning of Dialogue Strategies
Par :Formats :
- Paiement en ligne :
- Livraison à domicile ou en point Mondial Relay entre le 28 juin et le 8 juilletCet article doit être commandé chez un fournisseur. Votre colis vous sera expédié 8 à 17 jours après la date de votre commande.
- Retrait Click and Collect en magasin gratuit
- Livraison à domicile ou en point Mondial Relay entre le 28 juin et le 8 juillet
- Nombre de pages246
- PrésentationBroché
- Poids0.398 kg
- Dimensions16,0 cm × 24,0 cm × 1,3 cm
- ISBN2-930344-63-6
- EAN9782930344638
- Date de parution01/08/2005
- CollectionSimilar
- ÉditeurPresses Universitaires Louvain
Résumé
This book addresses the problems of spoken dialogue system design and especially automatic learning of optimal strategies for man-machine dialogues. Besides the description of the learning methods, this text proposes a framework for realistic simulation of human-machine dialogues based on probabilistic techniques, which allows automatic evaluation and unsupervised learning of dialogue strategies. This framework relies on stochastic modelling of modules composing spoken dialogue systems as well as on user modelling.
Special care has been taken to build models that can either be hand-tuned or learned from generic data.
Special care has been taken to build models that can either be hand-tuned or learned from generic data.
This book addresses the problems of spoken dialogue system design and especially automatic learning of optimal strategies for man-machine dialogues. Besides the description of the learning methods, this text proposes a framework for realistic simulation of human-machine dialogues based on probabilistic techniques, which allows automatic evaluation and unsupervised learning of dialogue strategies. This framework relies on stochastic modelling of modules composing spoken dialogue systems as well as on user modelling.
Special care has been taken to build models that can either be hand-tuned or learned from generic data.
Special care has been taken to build models that can either be hand-tuned or learned from generic data.