BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semiring Parsing without Parsing - Adam Lopez\, University of Edin
 burgh
DTSTART:20091120T120000Z
DTEND:20091120T130000Z
UID:TALK20472@talks.cam.ac.uk
CONTACT:Laura Rimell
DESCRIPTION:Machine translation\, summarization\, and parsing under most f
 ormalisms are examples of what is now popularly known as structured predic
 tion. Semiring parsing is an algorithmic framework that elegantly describe
 s structured problems: it combines deductive logic and probability\, clean
 ly separating model specification from statistical inference via generic d
 ynamic programming algorithms.  However\, two popular ingredients of moder
 n NLP systems are missing from the semiring parsing abstraction: non-local
  features and approximate inference. I'll talk about extending to semiring
  parsing to include these concepts\, including the case in which we don't 
 use dynamic programming at all.
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR