Building dialogue POMDPs from expert dialogues [electronic resource] : an end-to-end approach / Hamidreza Chinaei, Brahim Chaib-draa.

Unlimited

Authorized users

Can lend chapters, not whole ebooks

Building dialogue POMDPs from expert dialogues [electronic resource] : an end-to-end approach / Hamidreza Chinaei, Brahim Chaib-draa.

9783319262000 (electronic book)
3319262009 (electronic book)
9783319261980

Cham : Springer, 2016.

English

1 online resource.

10.1007/978-3-319-26200-0 doi

QA76.9.N38

006.35

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.

Includes bibliographical references.

Access limited to authorized users.

Online resource; title from PDF title page (viewed February 15, 2016)

SpringerBriefs in electrical and computer engineering. Speech technology.

Print version: 9783319261980

Online Resources > Ebooks
All Resources