BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Dialogue Act Prediction Using Stochastic Context-Free Grammar Indu
 ction - Jeroen Geertzen\, University of Cambridge
DTSTART:20090220T120000Z
DTEND:20090220T130000Z
UID:TALK17104@talks.cam.ac.uk
CONTACT:Johanna Geiss
DESCRIPTION:"In this talk I will describe a model-based approach to dialog
 ue\nmanagement\, which is guided by data-driven dialogue act prediction. T
 he\nstatistical prediction is based on stochastic context-free grammars\nt
 hat have been obtained by means of grammatical inference. The dialogue\nac
 t prediction is explored both for dialogue acts without realised\nsemantic
  content (consisting only of communicative functions) and for\ndialogue ac
 ts with realised semantic content. The approach improves\nover several n-g
 ram language models and can be used in isolation or for\nuser simulation i
 n reinforcement learning."
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR