BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning Syntactic Verb Frames Using Graphical Models - Tom Lippin
 cott\, University of Cambridge
DTSTART:20120622T110000Z
DTEND:20120622T113000Z
UID:TALK38357@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:This talk presents a novel approach for building verb subcateg
 orization\nlexicons using a simple graphical model.  In contrast to previo
 us\nmethods\, we show how the model can be trained without parsed input or
  a\npredefined subcategorization frame inventory.  Our method outperforms\
 nthe state-of-the-art on a verb clustering task\, and is easily trained on
 \narbitrary domains.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR