BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Guided Learning for Bidirectional Sequence Classification - Yue Z
 hang ()
DTSTART:20110210T120000Z
DTEND:20110210T130000Z
UID:TALK29773@talks.cam.ac.uk
CONTACT:Jimme Jardine
DESCRIPTION:This week Yue will be talking about:\n\nGuided Learning for Bi
 directional Sequence Classification\nhttp://www.aclweb.org/anthology-new/
 P/P07/P07-1096.pdf\n\n\nIn this paper\, we propose guided learning\, a new
  learning framework for bidirectional sequence classification. The tasks 
 of learning the order of inference and training the local classifier are 
 dynamically incorporated into a single Perceptron like learning algorithm.
  We apply this novel learning algorithm to POS tagging. It obtains an erro
 r rate of 2.67% on the standard PTB test set\, which represents 3.3% relat
 ive error reduction over the previous best result on the same data set\, w
 hile using fewer features.
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR