BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Are you losing Structures in Distributional Vectors? Smoothed Dist
 ributed Tree Kernels and the Convolution Conjecture - Fabio Massimo Zanzot
 to\, University of Rome &quot\;Tor Vergata&quot\;
DTSTART:20150306T120000Z
DTEND:20150306T130000Z
UID:TALK58356@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Syntax and words contribute to construct meaning of sentences.
  But\, compositional distributional semantics models (CDSMs) seem to compo
 se word meaning forgetting syntactic structures. Distributional vectors fo
 r sentences appear to carry only semantic information.\n\nIn this talk\, I
  propose the Convolution Conjecture and a novel structure-informed CDSM: t
 he Smoothed Distributed Tree Kernel. The Convolution Conjecture postulates
  an unexpected equivalence between semantic-driven CDSMs and structure-dri
 ven convolution kernels. The conjecture thus suggests that structures are 
 still encoded in distributional vectors. Building on this conjecture\, we 
 proposed the Smoothed Distributed Tree Kernel that combines structural syn
 tactic information and distributional semantics by clearly separating the 
 two. Our structure-informed CDSM is based on  Distributed Tree Kernels tha
 t embed syntactic structures in small vectors. We believe that the Convolu
 tion Conjecture and our Smoothed Distributed Tree Kernel could help in def
 ining a novel class of structure-informed CDSMs.\n\n\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR