BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Language Modelling - Carl Scheffler (University of Cam
 bridge)
DTSTART:20100823T100000Z
DTEND:20100823T110000Z
UID:TALK25632@talks.cam.ac.uk
CONTACT:Philip Sterne
DESCRIPTION:I will cover previous and new work on statistical language mod
 elling in two parts: character-based models and word-based models. The for
 mer have been used mostly for text compression and\, important to our grou
 p\, in Dasher. The latter are used for all manner of speech recognition an
 d text processing tasks. The focus will be on N-gram language models\, but
  I will also present some of my most recent work on incorporating prior sy
 ntactic and semantic information into these models in an attempt to improv
 e their predictive performance.
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR