ENGLISH

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

By Brahim Chaib-draa (auth.) , Hamidreza Chinaei

Book information

Publisher
Springer International Publishing
Year
2016
ISBN
978-3-319-26198-0, 978-3-319-26200-0
DOI
10.1007/978-3-319-26200-0
Language
english
Format
PDF
Filesize
2 MB (2031907 bytes)
Series
SpringerBriefs in Electrical and Computer Engineering
Edition
1
Pages
VII, 119\123
Time added
2016-03-14 21:35:01
Image and Speech Processing; User Interfaces and HNetworks; Artificial Intelligence (incl. Robotics)Signal

Description

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.

Similar books