Cargando…

Building dialogue POMDPs from expert dialogues: an end-to-end approach

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Chinaei, Hamidreza, Chaib-draa, Brahim
Lenguaje:eng
Publicado: Springer 2016
Materias:
Acceso en línea:https://dx.doi.org/10.1007/978-3-319-26200-0
http://cds.cern.ch/record/2137831
_version_ 1780950011309195264
author Chinaei, Hamidreza
Chaib-draa, Brahim
author_facet Chinaei, Hamidreza
Chaib-draa, Brahim
author_sort Chinaei, Hamidreza
collection CERN
description 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.
id cern-2137831
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2016
publisher Springer
record_format invenio
spelling cern-21378312021-04-21T19:46:10Zdoi:10.1007/978-3-319-26200-0http://cds.cern.ch/record/2137831engChinaei, HamidrezaChaib-draa, BrahimBuilding dialogue POMDPs from expert dialogues: an end-to-end approachEngineeringThis 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.Springeroai:cds.cern.ch:21378312016
spellingShingle Engineering
Chinaei, Hamidreza
Chaib-draa, Brahim
Building dialogue POMDPs from expert dialogues: an end-to-end approach
title Building dialogue POMDPs from expert dialogues: an end-to-end approach
title_full Building dialogue POMDPs from expert dialogues: an end-to-end approach
title_fullStr Building dialogue POMDPs from expert dialogues: an end-to-end approach
title_full_unstemmed Building dialogue POMDPs from expert dialogues: an end-to-end approach
title_short Building dialogue POMDPs from expert dialogues: an end-to-end approach
title_sort building dialogue pomdps from expert dialogues: an end-to-end approach
topic Engineering
url https://dx.doi.org/10.1007/978-3-319-26200-0
http://cds.cern.ch/record/2137831
work_keys_str_mv AT chinaeihamidreza buildingdialoguepomdpsfromexpertdialoguesanendtoendapproach
AT chaibdraabrahim buildingdialoguepomdpsfromexpertdialoguesanendtoendapproach