BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Tree-to-Tree Translation - David Chiang (University of Sou
 thern California)
DTSTART:20100201T130000Z
DTEND:20100201T140000Z
UID:TALK22971@talks.cam.ac.uk
CONTACT:Dr Marcus Tomalin
DESCRIPTION:Statistical translation models that try to capture the recursi
 ve structure of language have been widely adopted over the last few years.
  These models make use of varying amounts of information from linguistic t
 heory: some use none at all\, some use information about the grammar of th
 e target language\, some use information about the grammar of the source l
 anguage. But progress has been slower on tree-to-tree translation models: 
 models  that are able to learn the relationship between the grammars of bo
 th the source and target language. I will discuss the reasons why tree-to-
 tree translation has been a challenge\, review existing attempts at tree-t
 o-tree models\, and present some of our own work-in-progress on robustly m
 odeling source and target language syntax for significant improvements in 
 translation quality.
LOCATION:LR5\, Engineering Department\, Baker Building
END:VEVENT
END:VCALENDAR