BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Distributional Semantics and Kernels - Tamara Polajnar\, Universit
 y of Cambridge
DTSTART:20130222T120000Z
DTEND:20130222T130000Z
UID:TALK43456@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:This talk will cover some of my work which combines distributi
 onal\nmodels of lexical semantics with kernel methods.  I will be talking 
 how\ncombinations of models can be used to improve kernel classification. 
 In\nparticular\, I will talk about the use of HAL and BEAGLE lexical\nco-o
 ccurrence models and how they can be incorporated into a multiple\nkernel 
 learning framework to improve identification of protein-protein\ninteracti
 on sentences. Conversely\, I will be talking about the ways one\ncan use k
 ernel combinations to introduce inter-document similarity into\nExplicit S
 emantic Analysis.
LOCATION:FW11\, Computer Laboratory
END:VEVENT
END:VCALENDAR