BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Uncertainty and Learning in Spoken Human-Computer Dialogue - Blais
 e Thomson\, CUED MIL
DTSTART:20080310T130000Z
DTEND:20080310T140000Z
UID:TALK11067@talks.cam.ac.uk
CONTACT:Dr Marcus Tomalin
DESCRIPTION:In any spoken dialogue with a computer both speech recognition
  and semantic processing errors cause significant decreases in performance
 .  Recent work has suggested the Partially Observable Markov Decision Proc
 ess (POMDP) as a method for overcoming these difficulties. The POMDP model
  is able to capture the uncertainty inherent in dialogue and also  provide
 s a mechanism for the system to adapt and learn what to say in  which situ
 ation. While effective on small problems the POMDP approach has struggled 
 to scale to real world dialogues. This talk introduces an approach based o
 n the POMDP model which does scale. Bayesian Networks are used to implemen
 t efficient belief updates and special function  approximation techniques 
 with gradient based learning provide an effective learning algorithm. Simu
 lations show that the proposed framework outperforms standard techniques w
 henever errors increase.
LOCATION:LR5\, Engineering Department\, Baker Building
END:VEVENT
END:VCALENDAR