Un système de dialogue conversationnel doit aider les utilisateurs humains à atteindre leurs objectifs à travers des dialogues naturels et efficients. C'est une tache toutefois difficile car les langages naturels sont ambiguës et incertains, de plus le système de reconnaissance vocale (ASR) est bruité. À cela s'ajoute le fait que l'utilisateur humain peut changer son intention lors de l'interaction avec la machine. Dans ce contexte, l'application des processus décisionnels de Markov partiellement observables (POMDPs) au système de dialogue conversationnel nous a permis d'avoir un cadre formel pour représenter explicitement les incertitudes, et automatiser la politique d'optimisation. L'estimation des composantes du modelé d'un POMDP-dialogu...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
A dialogue system should give the machine the ability to interactnaturally and efficiently with huma...
This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in di...
Les systèmes de dialogue homme machine actuellement utilisés dans l’industrie sont fortement limités...
Spoken dialogue systems are gaining popularity with improvements in speech recognition technologies....
Abstract. In this paper, we learn the components of dialogue POMDP models from data. In particular, ...
The partially observable Markov decision process (POMDP) provides a popular framework for modelling ...
Partially Observable Markov Decision Processes (POMDPs) are attractive for dialogue management becau...
Dialog managers (DM) in spoken dialogue systems make decisions in highly uncertain conditions, due t...
A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enab...
A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enab...
Modelling dialogue as a Partially Observable Markov Decision Process (POMDP) enables a dialogue poli...
Abstract—Statistical dialogue systems are motivated by the need for a data-driven framework that red...
Un système de dialogue permet de doter la Machine de la capacité d'interagir de façon naturelle et e...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
A dialogue system should give the machine the ability to interactnaturally and efficiently with huma...
This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in di...
Les systèmes de dialogue homme machine actuellement utilisés dans l’industrie sont fortement limités...
Spoken dialogue systems are gaining popularity with improvements in speech recognition technologies....
Abstract. In this paper, we learn the components of dialogue POMDP models from data. In particular, ...
The partially observable Markov decision process (POMDP) provides a popular framework for modelling ...
Partially Observable Markov Decision Processes (POMDPs) are attractive for dialogue management becau...
Dialog managers (DM) in spoken dialogue systems make decisions in highly uncertain conditions, due t...
A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enab...
A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enab...
Modelling dialogue as a Partially Observable Markov Decision Process (POMDP) enables a dialogue poli...
Abstract—Statistical dialogue systems are motivated by the need for a data-driven framework that red...
Un système de dialogue permet de doter la Machine de la capacité d'interagir de façon naturelle et e...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
This paper presents a novel algorithm for learning parameters in statistical dialogue systems which ...
A dialogue system should give the machine the ability to interactnaturally and efficiently with huma...