Statistical methods for spoken dialogue management

Speech is the most natural mode of communication and yet attempts to build systems which support robust habitable conversations between a human and a machine have so far had only limited success. A key reason is that current systems treat speech input as equivalent to a keyboard or mouse, and behavi...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsman: Thomson, Blaise, 19..-
Materialtyp: Livre numérique
Språk:Anglais
Publicerad: London : Springer London 2013.
Cham : Springer Nature
Serie:Springer Theses, Recognizing Outstanding Ph.D. Research
Länkar:Accès sur la plateforme de l'éditeur
Accès sur la plateforme Istex
Accès Université d'Orléans
Accès INSA CVL
Anmärkning: Archives Springer e-books (Licence nationale)
Archives Springer e-books (Licence nationale)
Autres localisations: Voir dans le Sudoc
Edition sous un autre format:• Statistical Methods for Spoken Dialogue Management, Texte imprimé, 9781447149224
• Statistical Methods for Spoken Dialogue Management, Texte imprimé, 9781447149248
• Statistical Methods for Spoken Dialogue Management, Texte imprimé, 9781447159292
LEADER 03536nam a22003497a 4500
001 949556
008 130325s2013 xx ||| |||| 00| 0 eng d
009 PPN168294524
020 |a 9781447149231 
020 |a 9781447149231 
041 0 |a eng 
082 |a 621.382 
100 1 |a Thomson, Blaise,  |d 19..- 
245 1 0 |a Statistical methods for spoken dialogue management   |c by Blaise Thomson. 
260 |a London :  |b Springer London. 
260 |a Cham :  |b Springer Nature,  |c 2013. 
490 0 |a Springer Theses, Recognizing Outstanding Ph.D. Research  |x 2190-5061 
500 |a Archives Springer e-books (Licence nationale) 
500 |a Archives Springer e-books (Licence nationale) 
505 0 |a Dialogue system theory -- Maintaining state -- Maintaining state - optimizations -- Policy design -- Evaluation -- Parameter learning. 
506 |a Accès en ligne pour les établissements français bénéficiaires des licences nationales 
506 |a Accès soumis à abonnement pour tout autre établissement 
506 |a Conditions particulières de réutilisation pour les bénéficiaires des licences nationales. chttps://www.licencesnationales.fr/springer-nature-ebooks-contrat-licence-ln-2017 
520 |a Speech is the most natural mode of communication and yet attempts to build systems which support robust habitable conversations between a human and a machine have so far had only limited success. A key reason is that current systems treat speech input as equivalent to a keyboard or mouse, and behaviour is controlled by predefined scripts that try to anticipate what the user will say and act accordingly. But speech recognisers make many errors and humans are not predictable; the result is systems which are difficult to design and fragile in use. Statistical methods for spoken dialogue management takes a radically different view. It treats dialogue as the problem of inferring a user's intentions based on what is said. The dialogue is modelled as a probabilistic network and the input speech acts are observations that provide evidence for performing Bayesian inference. The result is a system which is much more robust to speech recognition errors and for which a dialogue strategy can be learned automatically using reinforcement learning. The thesis describes both the architecture, the algorithms needed for fast real-time inference over very large networks, model parameter estimation and policy optimisation. This ground-breaking work will be of interest both to practitioners in spoken dialogue systems and to cognitive scientists interested in models of human behaviour. 
776 0 |t Statistical Methods for Spoken Dialogue Management  |b Texte imprimé  |z 9781447149224 
776 0 |t Statistical Methods for Spoken Dialogue Management  |b Texte imprimé  |z 9781447149248 
776 0 |t Statistical Methods for Spoken Dialogue Management  |b Texte imprimé  |z 9781447159292 
856 4 |q PDF  |u https://doi.org/10.1007/978-1-4471-4923-1  |z Accès sur la plateforme de l'éditeur 
856 4 |u https://revue-sommaire.istex.fr/ark:/67375/8Q1-P57MRL7S-J  |z Accès sur la plateforme Istex 
856 4 |5 452349901:748124128  |u https://ezproxy.univ-orleans.fr/login?url=https://dx.doi.org/10.1007/978-1-4471-4923-1  |z Accès Université d'Orléans 
856 4 |5 180339901:751578819  |u https://ezproxy.insa-cvl.fr/login?qurl=https://dx.doi.org/10.1007/978-1-4471-4923-1  |z Accès INSA CVL 
997 |0 949556  |1 Livre numérique  |a Ressource numérique  |b INSA  |b ENSA  |c 0/Bibliothèque numérique/  |c 1/Bibliothèque numérique/Autre ressource numérique/