BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Categorical Compositionality for Distributional Semantics\, Withou
 t Tears - Edward Grefenstette\, University of Oxford
DTSTART:20110225T120000Z
DTEND:20110225T130000Z
UID:TALK29909@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:Coecke\, Sadrzadeh\, and Clark (arXiv:1003.4394v1 [cs.CL]) dev
 eloped a compositional model of meaning for distributional semantics\, in 
 which each word in a sentence has a meaning vector and the distributional 
 meaning of the sentence is a function of the tensor products of the word v
 ectors. Abstractly speaking\, this function is the morphism corresponding 
 to the grammatical structure of the sentence in the category of finite dim
 ensional vector spaces. In this paper\, we provide a concrete method for i
 mplementing this linear meaning map\, by constructing a corpus-based vecto
 r space for the type of sentence. Our construction method is based on stru
 ctured vector spaces whereby meaning vectors of all sentences\, regardless
  of their grammatical structure\, live in the same vector space. Our propo
 sed sentence space is the tensor product of two noun spaces\, in which the
  basis vectors are pairs of words each augmented with a grammatical role. 
 This enables us to compare meanings of sentences by simply taking the inne
 r product of their vectors.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR