BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Distributional semantics and beyond: Composition\, generation and 
 alignment - Georgiana Dinu\, University of Trento
DTSTART:20140801T110000Z
DTEND:20140801T120000Z
UID:TALK53573@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Distributional methods for semantics approximate the meaning o
 f linguistic expressions with vectors that summarize the contexts in which
  they occur in large samples of text. This has been a very successful appr
 oach to lexical semantics where semantic relatedness of words is assessed 
 by comparing vectors.  In this talk\, I will present work on extending dis
 tributional semantics in order to increase the range of semantic phenomena
  it can account for. In recent years\, distributional semantics models hav
 e been extended to the modelling of phrases and sentences through composit
 ion operations. I will motivate and explore the mirror problem of generati
 on: Given a distributional vector representing some meaning\, how can we g
 enerate the phrase that best expresses that meaning? In the second part of
  my talk I will introduce the problem of structure-preserving alignment of
  distributional semantic spaces\, discussing potential applications to bil
 ingual lexicon acquisition and language-vision interfaces.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR