Building Dialogue POMDPs from Expert Dialogues

Name: Building Dialogue POMDPs from Expert Dialogues
Author: Hamidreza Chinaei

An end-to-end approach

Specificaties

Paperback, blz. | Engels

Springer International Publishing | e druk, 2016

ISBN13: 9783319261980

Rubricering

Juridisch :

Springer International Publishing e druk, 2016 9783319261980

Onderdeel van serie SpringerBriefs in Speech Technology

€ 60,99

In winkelwagen

Levertijd ongeveer 9 werkdagen

Gratis verzonden

Samenvatting

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.

Specificaties

ISBN13:9783319261980

Taal:Engels

Bindwijze:paperback

Uitgever:Springer International Publishing

Serie:SpringerBriefs in Speech Technology

Inhoudsopgave

<p>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.</p>

Uw winkelwagen

Building Dialogue POMDPs from Expert Dialogues

An end-to-end approach

Samenvatting

Specificaties

Inhoudsopgave

Net verschenen

Rubrieken

Personen

Trefwoorden