BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Language in 3D: semantic tensor space - Tim Van de Croys - Univers
 ity of Cambridge
DTSTART:20110603T110000Z
DTEND:20110603T120000Z
UID:TALK31643@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:Distributional similarity methods have proven to be a valuable
  tool for the induction of semantic similarity. Up till now\, most algorit
 hms use two-way co-occurrence data to compute the meaning of words. Co-occ
 urrence frequencies\, however\, need not be pairwise. One can easily imagi
 ne situations where it is desirable to investigate co-occurrence frequenci
 es of three modes and beyond. In this presentation\, we will investigate t
 he use of tensors (the generalization of matrices) for the induction of la
 nguage models based on multi-way co-occurrences. Using tensors - combined 
 with appropriate factorization models - we are able to build semantically 
 richer language models\, that are useful in applications such as selection
 al preference induction and word sense discrimination.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR