BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Rebel Alliance in Babel's Aftermath: Combining rules and probabi
 lities in machine translation - Dan Flickinger\, CSLI Stanford University 
 and Cambridge Computer Laboratory
DTSTART:20071123T120000Z
DTEND:20071123T130000Z
UID:TALK8897@talks.cam.ac.uk
CONTACT:Johanna Geiss
DESCRIPTION:A Rebel Alliance in Babel's Aftermath: Combining rules and pro
 babilities in machine translation\n\nDate: Friday 23/11/2007\, 12.00pm. Ro
 om: SW01\n\n\n\nDuring the past 10 to 15 years\, machine translation has e
 xperienced renewed and growing interest\, driven in part by new applicatio
 ns and markets on the Web\, and in part by the invention of new approaches
 \, in particular data-driven methods like Statistical Machine Translation 
 (SMT) and Example-Based MT. While these methods have shown very promising 
 initial results\, it has recently become clear even to proponents of SMT t
 hat further improvements in quality of output will require something in ad
 dition to the current statistical methods alone. There is an emerging cons
 ensus within computational linguistics that hybrid approaches combining ri
 ch symbolic resources and powerful statistical techniques will be necessar
 y to produce NLP applications with a satisfactory balance of robustness an
 d precision. In this talk\, I will present and demonstrate one such hybrid
  approach in a semantic-transfer based MT system\, LOGON\, developed in No
 rway\, which makes use of two wide-coverage hand-built grammars of Norwegi
 an and English to parse and generate\, combined with statistical methods t
 o rank the outputs of each of the components for analysis\, transfer\, and
  generation.
LOCATION:SW01 Computer Laboratory
END:VEVENT
END:VCALENDAR