000 03572nam a22006017a 4500
001 sulb-eb0021603
003 BD-SySUS
005 20160413122151.0
007 cr nn 008mamaa
008 130109s2013 xxk| s |||| 0|eng d
020 _a9781447149231
_9978-1-4471-4923-1
024 7 _a10.1007/978-1-4471-4923-1
_2doi
050 4 _aTK5102.9
050 4 _aTA1637-1638
050 4 _aTK7882.S65
072 7 _aTTBM
_2bicssc
072 7 _aUYS
_2bicssc
072 7 _aTEC008000
_2bisacsh
072 7 _aCOM073000
_2bisacsh
082 0 4 _a621.382
_223
100 1 _aThomson, Blaise.
_eauthor.
245 1 0 _aStatistical Methods for Spoken Dialogue Management
_h[electronic resource] /
_cby Blaise Thomson.
264 1 _aLondon :
_bSpringer London :
_bImprint: Springer,
_c2013.
300 _aXVIII, 138 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSpringer Theses, Recognizing Outstanding Ph.D. Research,
_x2190-5053
505 0 _aDialogue system theory -- Maintaining state -- Maintaining state - optimizations -- Policy design -- Evaluation -- Parameter learning.
520 _aSpeech 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.
650 0 _aEngineering.
650 0 _aMathematical statistics.
650 0 _aStatistics.
650 0 _aNeuropsychology.
650 0 _aBiological psychology.
650 0 _aCognitive psychology.
650 1 4 _aEngineering.
650 2 4 _aSignal, Image and Speech Processing.
650 2 4 _aStatistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences.
650 2 4 _aProbability and Statistics in Computer Science.
650 2 4 _aNeuropsychology.
650 2 4 _aBiological Psychology.
650 2 4 _aCognitive Psychology.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9781447149224
830 0 _aSpringer Theses, Recognizing Outstanding Ph.D. Research,
_x2190-5053
856 4 0 _uhttp://dx.doi.org/10.1007/978-1-4471-4923-1
912 _aZDB-2-ENG
942 _2Dewey Decimal Classification
_ceBooks
999 _c43695
_d43695