Statistical Methods for Spoken Dialogue Management (Record no. 56562)

000 -LEADER
fixed length control field 03542nam a22006015i 4500
001 - CONTROL NUMBER
control field 978-1-4471-4923-1
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20200421112040.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 130109s2013 xxk| s |||| 0|eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
ISBN 9781447149231
-- 978-1-4471-4923-1
082 04 - CLASSIFICATION NUMBER
Call Number 621.382
100 1# - AUTHOR NAME
Author Thomson, Blaise.
245 10 - TITLE STATEMENT
Title Statistical Methods for Spoken Dialogue Management
300 ## - PHYSICAL DESCRIPTION
Number of Pages XVIII, 138 p.
490 1# - SERIES STATEMENT
Series statement Springer Theses, Recognizing Outstanding Ph.D. Research,
505 0# - FORMATTED CONTENTS NOTE
Remark 2 Dialogue system theory -- Maintaining state -- Maintaining state - optimizations -- Policy design -- Evaluation -- Parameter learning.
520 ## - SUMMARY, ETC.
Summary, etc Speech is the most natural mode of communication and yet attempts to build systems which support robust habitable conversations between a human and a machine have so far had only limited success. A key reason is that current systems treat speech input as equivalent to a keyboard or mouse, and behaviour is controlled by predefined scripts that try to anticipate what the user will say and act accordingly. But speech recognisers make many errors and humans are not predictable; the result is systems which are difficult to design and fragile in use. Statistical methods for spoken dialogue management takes a radically different view. It treats dialogue as the problem of inferring a user's intentions based on what is said. The dialogue is modelled as a probabilistic network and the input speech acts are observations that provide evidence for performing Bayesian inference. The result is a system which is much more robust to speech recognition errors and for which a dialogue strategy can be learned automatically using reinforcement learning. The thesis describes both the architecture, the algorithms needed for fast real-time inference over very large networks, model parameter estimation and policy optimisation. This ground-breaking work will be of interest both to practitioners in spoken dialogue systems and to cognitive scientists interested in models of human behaviour.
856 40 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier http://dx.doi.org/10.1007/978-1-4471-4923-1
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type eBooks
264 #1 -
-- London :
-- Springer London :
-- Imprint: Springer,
-- 2013.
336 ## -
-- text
-- txt
-- rdacontent
337 ## -
-- computer
-- c
-- rdamedia
338 ## -
-- online resource
-- cr
-- rdacarrier
347 ## -
-- text file
-- PDF
-- rda
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Engineering.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Mathematical statistics.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Statistics.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Neuropsychology.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Biological psychology.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Cognitive psychology.
650 14 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Engineering.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Signal, Image and Speech Processing.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Probability and Statistics in Computer Science.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Neuropsychology.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Biological Psychology.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Cognitive Psychology.
830 #0 - SERIES ADDED ENTRY--UNIFORM TITLE
-- 2190-5053
912 ## -
-- ZDB-2-ENG

No items available.