BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:NLP Reading Group: Measuring Distributional Similarity in Context 
 - Marek Rei (University of Cambridge)
DTSTART:20120308T120000Z
DTEND:20120308T130000Z
UID:TALK36907@talks.cam.ac.uk
CONTACT:Marek Rei
DESCRIPTION:This week Marek will be talking about:\n\nMeasuring Distributi
 onal Similarity in Context. \nGeorgiana Dinu & Mirella Lapata. \nEMNLP 201
 0\n\nPDF: http://aclweb.org/anthology-new/D/D10/D10-1113.pdf\n\nThe comput
 ation of meaning similarity as operationalized by vector-based models has 
 found widespread use in many tasks ranging from the acquisition of synonym
 s and paraphrases to word sense disambiguation and textual entailment. Vec
 tor-based models are typically directed at representing words in isolation
  and thus best suited for measuring similarity out of context. In his pape
 r we propose a probabilistic framework for measuring similarity in context
 . Central to our approach is the intuition that word meaning is represente
 d as a probability distribution over a set of latent senses and is modulat
 ed by context. Experimental results on lexical substitution and word simil
 arity show that our algorithm outperforms previously proposed models.
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR