BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Improving &amp\; Better Understanding Word Vector Representations 
 - Manaal Faruqui\, Carnegie Mellon University
DTSTART:20150619T110000Z
DTEND:20150619T120000Z
UID:TALK59678@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Data-driven learning of distributional word vector representat
 ions is a technique of central importance in natural language processing. 
 In this talk\, we will explore several questions and their solutions that 
 are aimed at improving and better understanding distributional word vector
 s. Can word vectors benefit from information stored in semantic lexicons?\
 nCan these word vectors look similar to features typically used in NLP? Do
  the vector dimensions have certain meaning associated with them or are th
 ey uninterpretable? Is it necessary to develop word vectors using distribu
 tional context?\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR