Central Library

Normal view MARC view ISBD view

Building Dialogue POMDPs from Expert Dialogues [electronic resource] : An end-to-end approach / by Hamidreza Chinaei, Brahim Chaib-draa.

By: Chinaei, Hamidreza [author.].
Contributor(s): Chaib-draa, Brahim [author.] | SpringerLink (Online service).
Material type: materialTypeLabelBookSeries: SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning: Publisher: Cham : Springer International Publishing : Imprint: Springer, 2016Edition: 1st ed. 2016.Description: VII, 119 p. 22 illus., 21 illus. in color. online resource.Content type: text Media type: computer Carrier type: online resourceISBN: 9783319262000.Subject(s): Signal processing | User interfaces (Computer systems) | Human-computer interaction | Telecommunication | Artificial intelligence | Computational linguistics | Signal, Speech and Image Processing | User Interfaces and Human Computer Interaction | Communications Engineering, Networks | Artificial Intelligence | Computational LinguisticsAdditional physical formats: Printed edition:: No title; Printed edition:: No titleDDC classification: 621.382 Online resources: Click here to access online
Contents:
1 Introduction -- 2 A few words on topic modeling -- 3 Sequential decision making in spoken dialog management -- 4 Learning the dialog POMDP model components -- 5 Learning the reward function -- 6 Application on healthcare dialog management -- 7 Conclusions and future work.
In: Springer Nature eBookSummary: This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in dialogue systems. It presents POMDP as a formal framework to represent uncertainty explicitly while supporting automated policy solving. The authors propose and implement an end-to-end learning approach for dialogue POMDP model components. Starting from scratch, they present the state, the transition model, the observation model and then finally the reward model from unannotated and noisy dialogues. These altogether form a significant set of contributions that can potentially inspire substantial further work. This concise manuscript is written in a simple language, full of illustrative examples, figures, and tables. Provides insights on building dialogue systems to be applied in real domain Illustrates learning dialogue POMDP model components from unannotated dialogues in a concise format Introduces an end-to-end approach that makes use of unannotated and noisy dialogue for learning each component of dialogue POMDPs.
    average rating: 0.0 (0 votes)
No physical items for this record

1 Introduction -- 2 A few words on topic modeling -- 3 Sequential decision making in spoken dialog management -- 4 Learning the dialog POMDP model components -- 5 Learning the reward function -- 6 Application on healthcare dialog management -- 7 Conclusions and future work.

This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in dialogue systems. It presents POMDP as a formal framework to represent uncertainty explicitly while supporting automated policy solving. The authors propose and implement an end-to-end learning approach for dialogue POMDP model components. Starting from scratch, they present the state, the transition model, the observation model and then finally the reward model from unannotated and noisy dialogues. These altogether form a significant set of contributions that can potentially inspire substantial further work. This concise manuscript is written in a simple language, full of illustrative examples, figures, and tables. Provides insights on building dialogue systems to be applied in real domain Illustrates learning dialogue POMDP model components from unannotated dialogues in a concise format Introduces an end-to-end approach that makes use of unannotated and noisy dialogue for learning each component of dialogue POMDPs.

There are no comments for this item.

Log in to your account to post a comment.