000			03873nam a22006255i 4500
001			978-3-319-26200-0
003			DE-He213
005			20220801215016.0
007			cr nn 008mamaa
008			160208s2016 sz | s |||| 0|eng d
020			_a9783319262000 _9978-3-319-26200-0
024	7		_a10.1007/978-3-319-26200-0 _2doi
050		4	_aTK5102.9
072		7	_aTJF _2bicssc
072		7	_aUYS _2bicssc
072		7	_aTEC008000 _2bisacsh
072		7	_aTJF _2thema
072		7	_aUYS _2thema
082	0	4	_a621.382 _223
100	1		_aChinaei, Hamidreza. _eauthor. _4aut _4http://id.loc.gov/vocabulary/relators/aut _941780
245	1	0	_aBuilding Dialogue POMDPs from Expert Dialogues _h[electronic resource] : _bAn end-to-end approach / _cby Hamidreza Chinaei, Brahim Chaib-draa.
250			_a1st ed. 2016.
264		1	_aCham : _bSpringer International Publishing : _bImprint: Springer, _c2016.
300			_aVII, 119 p. 22 illus., 21 illus. in color. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
490	1		_aSpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning, _x2191-7388
505	0		_a1 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			_aThis 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	_aSignal processing. _94052
650		0	_aUser interfaces (Computer systems). _911681
650		0	_aHuman-computer interaction. _96196
650		0	_aTelecommunication. _910437
650		0	_aArtificial intelligence. _93407
650		0	_aComputational linguistics. _96146
650	1	4	_aSignal, Speech and Image Processing . _931566
650	2	4	_aUser Interfaces and Human Computer Interaction. _931632
650	2	4	_aCommunications Engineering, Networks. _931570
650	2	4	_aArtificial Intelligence. _93407
650	2	4	_aComputational Linguistics. _96146
700	1		_aChaib-draa, Brahim. _eauthor. _4aut _4http://id.loc.gov/vocabulary/relators/aut _941781
710	2		_aSpringerLink (Online service) _941782
773	0		_tSpringer Nature eBook
776	0	8	_iPrinted edition: _z9783319261980
776	0	8	_iPrinted edition: _z9783319261997
830		0	_aSpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning, _x2191-7388 _941783
856	4	0	_uhttps://doi.org/10.1007/978-3-319-26200-0
912			_aZDB-2-ENG
912			_aZDB-2-SXE
942			_cEBK
999			_c77006 _d77006