BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Functional Distributional Semantics - Guy Edward Toh Emerson (Univ
 ersity of Cambridge)
DTSTART:20170609T110000Z
DTEND:20170609T120000Z
UID:TALK72611@talks.cam.ac.uk
CONTACT:Anita Verő
DESCRIPTION:Vector space models have become popular in computational lingu
 istics\, despite the challenges they face when it comes to compositionalit
 y\, inference\, context-dependence\, and other issues of interest to seman
 ticists.  I will present a probabilistic framework which draws on both for
 mal semantics and recent advances in machine learning. In particular\, we 
 can separate predicates from the entities they refer to\, and represent pr
 edicates not by vectors\, but by *functions*.  From a formal semantic poin
 t of view\, these can be seen as truth-conditional functions\, and from a 
 machine learning point of view\, these can be seen as classifiers.  By def
 ining a probabilistic graphical model incorporating such functions\, we ca
 n recast many semantic phenomena in terms of Bayesian inference.  After de
 scribing the framework\, and its implementation with neural networks\, I w
 ill present recent results showing that such model can learn information n
 ot captured by vector space models.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR