BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Natural Language Processing Reading Group
SUMMARY:Speed and Accuracy in Shallow and Deep Stochastic 
 Parsing - Ted Briscoe and Steve Clark
DTSTART;TZID=Europe/London:20091109T123000
DTEND;TZID=Europe/London:20091109T133000
UID:TALK21368AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/21368
DESCRIPTION:At this session of the NLIP Reading Group we'll be
  discussing the following paper:\n\nRonald M. Kapl
 an\, Stefan Riezler\, Tracy Holloway King\, John T
 . Maxwell III\, Alexander Vasserman and Richard Cr
 ouch. 2004. "Speed and Accuracy in Shallow and Dee
 p Stochastic Parsing":http://aclweb.org/anthology-
 new/N/N04/N04-1013.pdf. In Proceedings of NAACL-HL
 T-04.\n\n*Abstract:*\nThis paper reports some expe
 riments that compare the accuracy and performance 
 of two stochastic parsing systems. The currently p
 opular Collins parser is a shallow parser whose ou
 tput contains more detailed semantically relevant 
 information than other such parsers. The XLE parse
 r is a deep-parsing system that couples a Lexical 
 Functional Grammar to a loglinear disambiguation c
 omponent and provides much richer representations 
 theory. We measured the accuracy of both systems a
 gainst a gold standard of the PARC 700 dependency 
 bank\, and also measured their processing times. W
 e found the deep-parsing system to be more\naccura
 te than the Collins parser with only a slight redu
 ction in parsing speed. 
LOCATION:GS15\, Computer Laboratory
CONTACT:Diarmuid Ó Séaghdha
END:VEVENT
END:VCALENDAR