000753759 000__ 03149cam\a2200481Ii\4500
000753759 001__ 753759
000753759 005__ 20230306141518.0
000753759 006__ m\\\\\o\\d\\\\\\\\
000753759 007__ cr\cn\nnnunnun
000753759 008__ 160211s2016\\\\sz\\\\\\ob\\\\000\0\eng\d
000753759 020__ $$a9783319262000$$q(electronic book)
000753759 020__ $$a3319262009$$q(electronic book)
000753759 020__ $$z9783319261980
000753759 0247_ $$a10.1007/978-3-319-26200-0$$2doi
000753759 035__ $$aSP(OCoLC)ocn938557234
000753759 035__ $$aSP(OCoLC)938557234
000753759 040__ $$aN$T$$beng$$erda$$epn$$cN$T$$dN$T$$dGW5XE$$dIDEBK$$dEBLCP$$dCDX$$dAZU$$dYDXCP$$dOCLCF$$dDEBSZ$$dCOO$$dOCLCA
000753759 049__ $$aISEA
000753759 050_4 $$aQA76.9.N38
000753759 08204 $$a006.35$$223
000753759 1001_ $$aChinaei, Hamiza,$$eauthor.
000753759 24510 $$aBuilding dialogue POMDPs from expert dialogues$$h[electronic resource] :$$ban end-to-end approach /$$cHamidreza Chinaei, Brahim Chaib-draa.
000753759 264_1 $$aCham :$$bSpringer,$$c2016.
000753759 300__ $$a1 online resource.
000753759 336__ $$atext$$btxt$$2rdacontent
000753759 337__ $$acomputer$$bc$$2rdamedia
000753759 338__ $$aonline resource$$bcr$$2rdacarrier
000753759 4901_ $$aSpringerBriefs in electrical and computer engineering. Speech technology
000753759 504__ $$aIncludes bibliographical references.
000753759 5050_ $$a1 Introduction -- 2 A few words on topic modeling -- 3 Sequential decision making in spoken dialog management -- 4 Learning the dialog POMDP model components -- 5 Learning the reward function -- 6 Application on healthcare dialog management -- 7 Conclusions and future work.
000753759 506__ $$aAccess limited to authorized users.
000753759 520__ $$aThis book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in dialogue systems. It presents POMDP as a formal framework to represent uncertainty explicitly while supporting automated policy solving. The authors propose and implement an end-to-end learning approach for dialogue POMDP model components. Starting from scratch, they present the state, the transition model, the observation model and then finally the reward model from unannotated and noisy dialogues. These altogether form a significant set of contributions that can potentially inspire substantial further work. This concise manuscript is written in a simple language, full of illustrative examples, figures, and tables. Provides insights on building dialogue systems to be applied in real domain Illustrates learning dialogue POMDP model components from unannotated dialogues in a concise format Introduces an end-to-end approach that makes use of unannotated and noisy dialogue for learning each component of dialogue POMDPs.
000753759 588__ $$aOnline resource; title from PDF title page (viewed February 15, 2016)
000753759 650_0 $$aNatural language processing (Computer science)
000753759 650_0 $$aSpeech processing systems.
000753759 650_0 $$aMarkov processes.
000753759 7001_ $$aChaib-draa, Brahim,$$eauthor.
000753759 77608 $$iPrint version:$$z9783319261980
000753759 830_0 $$aSpringerBriefs in electrical and computer engineering.$$pSpeech technology.
000753759 852__ $$bebk
000753759 85640 $$3SpringerLink$$uhttps://univsouthin.idm.oclc.org/login?url=http://link.springer.com/10.1007/978-3-319-26200-0$$zOnline Access$$91397441.1
000753759 909CO $$ooai:library.usi.edu:753759$$pGLOBAL_SET
000753759 980__ $$aEBOOK
000753759 980__ $$aBIB
000753759 982__ $$aEbook
000753759 983__ $$aOnline
000753759 994__ $$a92$$bISE