BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Compositionality modelling and non-compositionality detection with
  distributional semantics - Diana McCarthy\, University of Cambridge
DTSTART:20121109T120000Z
DTEND:20121109T130000Z
UID:TALK40794@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:Distributional similarity has been used as a proxy for modelli
 ng lexical\nsemantics for nearly two decades.  There is now  a significant
  and\ngrowing interest in  moving these models from lexical to  phrasal\ns
 emantics. For just under one decade\, many computational linguistics\nrese
 archers have applied distributional semantics to the task of\ndetecting no
 n-compositionality of candidate multiwords.  In this talk\, I\nwill give a
 n overview of my work in this area. I will focus on the more\nrecent work 
 I have collaborated on\, with Siva Reddy and colleagues\,\nwhich borrows t
 echniques from the state-of-the-art compositional\ndistributional models f
 or non-compositionality detection. Ultimately\,\nthese distributional mode
 ls of phrasal semantics will need to be\nextended to incorporate non-compo
 sitionality.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR