BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Properties and Applications of Word Tensors - Mehrnoos
 h Sadrzadeh (Queen Mary University of London)
DTSTART:20170601T100000Z
DTEND:20170601T110000Z
UID:TALK72515@talks.cam.ac.uk
CONTACT:Mohammad Taher Pilehvar
DESCRIPTION:Compositional distributional semantics represents meanings of 
 phrases and sentences by vectors built from representations of the words t
 herein. The categorical framework of Clark\, Coecke\, and myself offers a 
 method whereby one builds these vectors by transforming the grammatical st
 ructure of the phrase/sentence into a linear map. In this framework\, mean
 ings of words with functional types become matrices\, cubes\, and in gener
 al higher order tensors. The work of Grefenstette\, Kartsaklis\, and I sho
 wed how different instantiations of the framework improve tasks such as ph
 rase/sentence disambiguation\,   similarity\, and entailment. In recent wo
 rk with Blundell and Jezek we show how these models are also helpful at th
 e word level by employing them  in the verb similarity task of Gerz et al.
  With Kartsaklis and Ramgoolam\, we propose that perturbed Gaussian models
  with permutation symmetry provide a framework for characterizing the stat
 istical properties of the word tensors. In this talk\, we will present the
  categorical framework and go through snippets of the experiments\, with f
 ocus on the latter two recent advances. 
LOCATION: SR-24\, English Faculty Building\, 9 West Road (Sidgwick Site)
END:VEVENT
END:VCALENDAR