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

• Κύριοι συγγραφείς: Chinaei, Hamidreza (Συγγραφέας), Chaib-draa, Brahim (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2016.
• Έκδοση: 1st ed. 2016.
• Σειρά: SpringerBriefs in Electrical and Computer Engineering,
• Θέματα: Engineering.; User interfaces (Computer systems).; Artificial intelligence.; Computational linguistics.; Electrical engineering.; Signal, Image and Speech Processing.; User Interfaces and Human Computer Interaction.; Communications Engineering, Networks.; Artificial Intelligence (incl. Robotics).; Computational Linguistics.

 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. 

 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.