國立高雄大學圖資館 |

Language: English

Back

Building dialogue POMDPs from expert...

Chaib-draa, Brahim.

Building dialogue POMDPs from expert dialoguesan end-to-end approach /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Building dialogue POMDPs from expert dialoguesby Hamidreza Chinaei, Brahim Chaib-draa.
Reminder of title:	an end-to-end approach /
Author:	Chinaei, Hamidreza.
other author:	Chaib-draa, Brahim.
Published:	Cham :Springer International Publishing :2016.
Description:	vii, 119 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Natural language processing (Computer science)
Online resource:	http://dx.doi.org/10.1007/978-3-319-26200-0
ISBN:	9783319262000$q(electronic bk.)

Building dialogue POMDPs from expert dialoguesan end-to-end approach /
Chinaei, Hamidreza.

Building dialogue POMDPs from expert dialoguesan end-to-end approach /[electronic resource] :by Hamidreza Chinaei, Brahim Chaib-draa. - Cham :Springer International Publishing :2016. - vii, 119 p. :ill., digital ;24 cm. - SpringerBriefs in electrical and computer engineering,2191-8112. - SpringerBriefs in electrical and computer engineering..

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.

ISBN: 9783319262000$q(electronic bk.)

Standard No.: 10.1007/978-3-319-26200-0doiSubjects--Topical Terms:

200539
Natural language processing (Computer science)

LC Class. No.: QA76.9.N38

Dewey Class. No.: 006.35

Building dialogue POMDPs from expert dialoguesan end-to-end approach /
LDR:02413nmm a2200349 a 4500 001 483328
003 DE-He213
005 20160824155648.0
006 m d
007 cr nn 008maaau
008 161007s2016 gw s 0 eng d
020 $a 9783319262000$q(electronic bk.)
020 $a 9783319261980$q(paper)
024 7 $a 10.1007/978-3-319-26200-0 $2 doi
035 $a 978-3-319-26200-0
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.9.N38
072 7 $a TTBM $2 bicssc
072 7 $a UYS $2 bicssc
072 7 $a TEC008000 $2 bisacsh
072 7 $a COM073000 $2 bisacsh
082 0 4 $a 006.35 $2 23
090 $a QA76.9.N38 $b C539 2016
100 1 $a Chinaei, Hamidreza. $3 740826
245 1 0 $a Building dialogue POMDPs from expert dialogues $h [electronic resource] : $b an end-to-end approach / $c by Hamidreza Chinaei, Brahim Chaib-draa.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2016.
300 $a vii, 119 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in electrical and computer engineering, $x 2191-8112
505 0 $a 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.
520 $a 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.
650 0 $a Natural language processing (Computer science) $3 200539
650 0 $a Speech processing systems. $3 184755
650 0 $a Markov processes. $3 181910
650 2 4 $a Engineering. $3 210888
650 2 4 $a Signal, Image and Speech Processing. $3 273768
650 2 4 $a User Interfaces and Human Computer Interaction. $3 274517
650 2 4 $a Communications Engineering, Networks. $3 273745
650 2 4 $a Artificial Intelligence (incl. Robotics) $3 252959
650 2 4 $a Computational Linguistics. $3 274669
700 1 $a Chaib-draa, Brahim. $3 260871
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a SpringerBriefs in electrical and computer engineering. $3 557682
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-26200-0
950 $a Engineering (Springer-11647)