BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Looking for hyponyms in vector space - Marek Rei\, SwiftKey 
DTSTART:20140605T113000Z
DTEND:20140605T120000Z
UID:TALK52794@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:The task of detecting and generating hyponyms is at the core o
 f semantic understanding of language\, and has numerous practical applicat
 ions.\nWe investigate how neural network embeddings perform on this task\,
  compared to dependency-based vector space models\, and evaluate a range o
 f similarity measures on hyponym generation. \nA new asymmetric similarity
  measure and a combination approach are described\, both of which signific
 antly improve precision. We release three new datasets of lexical vector r
 epresentations trained on the BNC and our evaluation dataset for hyponym g
 eneration.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR