國立虎尾科技大學 |

Building Dialogue POMDPs from Expert Dialogues = An end-to-end approach /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Building Dialogue POMDPs from Expert Dialogues/ by Hamidreza Chinaei, Brahim Chaib-draa.
其他題名:	An end-to-end approach /
作者:	Chinaei, Hamidreza.
其他作者:	Chaib-draa, Brahim.
面頁冊數:	VII, 119 p. 22 illus., 21 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Signal processing. -
電子資源:	https://doi.org/10.1007/978-3-319-26200-0
ISBN:	9783319262000

Building Dialogue POMDPs from Expert Dialogues = An end-to-end approach /
Chinaei, Hamidreza.

Building Dialogue POMDPs from Expert DialoguesAn end-to-end approach /[electronic resource] :by Hamidreza Chinaei, Brahim Chaib-draa. - 1st ed. 2016. - VII, 119 p. 22 illus., 21 illus. in color.online resource. - SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning,2191-737X. - SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning,.

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

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

561459
Signal processing.

LC Class. No.: TK5102.9

Dewey Class. No.: 621.382

Building Dialogue POMDPs from Expert Dialogues = An end-to-end approach /
LDR:02838nam a22004215i 4500 001 972425
003 DE-He213
005 20200703014754.0
007 cr nn 008mamaa
008 201211s2016 gw | s |||| 0|eng d
020 $a 9783319262000 $9 978-3-319-26200-0
024 7 $a 10.1007/978-3-319-26200-0 $2 doi
035 $a 978-3-319-26200-0
050 4 $a TK5102.9
050 4 $a TA1637-1638
072 7 $a TTBM $2 bicssc
072 7 $a TEC008000 $2 bisacsh
072 7 $a TTBM $2 thema
072 7 $a UYS $2 thema
082 0 4 $a 621.382 $2 23
100 1 $a Chinaei, Hamidreza. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1105959
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.
250 $a 1st ed. 2016.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2016.
300 $a VII, 119 p. 22 illus., 21 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning, $x 2191-737X
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 Signal processing. $3 561459
650 0 $a Image processing. $3 557495
650 0 $a Speech processing systems. $3 564428
650 0 $a User interfaces (Computer systems). $3 1253526
650 0 $a Electrical engineering. $3 596380
650 0 $a Artificial intelligence. $3 559380
650 0 $a Computational linguistics. $3 555811
650 1 4 $a Signal, Image and Speech Processing. $3 670837
650 2 4 $a User Interfaces and Human Computer Interaction. $3 669793
650 2 4 $a Communications Engineering, Networks. $3 669809
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Computational Linguistics. $3 670080
700 1 $a Chaib-draa, Brahim. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1105960
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783319261980
776 0 8 $i Printed edition: $z 9783319261997
830 0 $a SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning, $x 2191-737X $3 1255129
856 4 0 $u https://doi.org/10.1007/978-3-319-26200-0
912 $a ZDB-2-ENG
912 $a ZDB-2-SXE
950 $a Engineering (SpringerNature-11647)
950 $a Engineering (R0) (SpringerNature-43712)