BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probabilistic Programming and Probabilistic Databases for Large-sc
 ale Knowledge-base Construction - Andrew McCallum\, University of Massachu
 setts Amherst
DTSTART:20120619T120000Z
DTEND:20120619T130000Z
UID:TALK38634@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Wikipedia’s impact has been revolutionary. The collaborative
 ly edited encyclopedia has transformed the way many people learn\, browse 
 new interests\, share knowledge and make decisions. Its information is mai
 nly represented in natural language text. However\, for many tasks more st
 ructured information is useful because it better supports pattern analysis
  and decision-making. In this talk I will describe multiple research compo
 nents useful for building large\, structured knowledge bases\, including i
 nformation extraction from text\, entity resolution\, joint inference with
  conditional random fields\, probabilistic databases to manage uncertainty
  at scale\, robust reasoning about human edits\, tight integration of prob
 abilistic inference and parallel/distributed processing\, and probabilisti
 c programming languages for easy specification of complex graphical models
 . I will also discuss applications of these methods to scientometrics and 
 a new publishing model for science research.\n\nJoint work with Michael Wi
 ck\, Sameer Singh\, Karl Schultz\, Sebastian Riedel\, Limin Yao\, Brian Ma
 rtin and Gerome Miklau.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR