@InCollection{Supelec630,
author = {Senthilkumar Chandramohan and Olivier Pietquin},
title = {{User and Noise Adaptive Dialogue Management Using Hybrid System Actions}},
year = {2010},
booktitle = {{Spoken Dialogue Systems for Ambient Environments}},
publisher = {Springer Verlag, Heidelberg - Berlin},
volume = {6392},
pages = {13-24},
month = {October},
note = {Proceedings of the International Workshop on Spoken Dialogue Systems (IWSDS 2010)},
editor = {Gary Geunbae Lee and Joseph Mariani and Wolfgang Minker and Satoshi Nakamura},
series = {Lecture Notes in Artificial Intelligence (LNAI)},
address = {Gotemba, Shizuoka (Japan)},
url = {http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/IWSDS_2010_SCOP.pdf},
isbn = {978-3-642-16201-5},
abstract = {In recent years reinforcement-learning-based approaches have
been
widely used for management policy optimization in spoken
dialogue systems
(SDS). A dialogue management policy is a mapping from dialogue
states to system
actions, i.e. given the state of the dialogue the dialogue
policy determines the
next action to be performed by the dialogue manager. So-far
policy optimization
primarily focused on mapping the dialogue state to simple
system actions (such
as confirm or ask one piece of information) and the possibility
of using complex
system actions (such as confirm or ask several slots at the
same time) has not been
well investigated. In this paper we explore the possibilities
of using complex (or
hybrid) system actions for dialogue management and then discuss
the impact of
user experience and channel noise on complex action selection.
Our experimental
results obtained using simulated users reveal that user and
noise adaptive hybrid
action selection can perform better than dialogue policies
which can only perform
simple actions.}
}