BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Fast Decoder for Joint Word Segmentation and POS-Tagging using a
  Single Discriminative Model - Yue Zhang and Stephen Clark\, University of
  Cambridge
DTSTART:20101001T113000Z
DTEND:20101001T120000Z
UID:TALK26905@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:We show that the standard beam-search algorithm can be used as
  an efficient decoder for the global linear model of Zhang and Clark (2008
 ) for joint word segmentation and POS-tagging\, achieving a significant sp
 eed improvement. Such decoding is enabled by: (1) separating full word fea
 tures from partial word features so that feature templates can be instanti
 ated incrementally\, according to whether the current character is separat
 ed or appended\; (2) deciding the POS-tag of a potential word when its fir
 st character is processed. Early-update is used with perceptron training s
 o that the linear model gives a high score to a correct partial candidate 
 as well as a full output.  Effective scoring of partial structures allows 
 the decoder to give high accuracy with a small beam-size of 16. In our 10-
 fold cross-validation experiments with the Chinese Treebank\, our system p
 erformed over 10 times as fast as Zhang and Clark (2008) with little accur
 acy loss. The accuracy of our system on the standard CTB 5 test was compet
 itive with the best in the literature.\n
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR