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:Frustratingly easy domain adaptation - Lin Sun (Co
 mputer Laboratory)
DTSTART;TZID=Europe/London:20090112T123000
DTEND;TZID=Europe/London:20090112T133000
UID:TALK16252AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/16252
DESCRIPTION:At this session of the NLIP Reading Group we'll be
  discussing the following paper:\n\nHal Daumé III.
  2007. "Frustratingly easy domain adaptation":http
 ://hal3.name/docs/daume07easyadapt.pdf. In Proceed
 ings of the 45th Annual Meeting of the Association
  of Computational Linguistics (ACL-07).\n\n*Abstra
 ct:*\nWe describe an approach to domain adaptation
  that is appropriate exactly in the case when one 
 has enough "target" data to do slightly better tha
 n just using only "source" data.  Our approach is 
 incredibly simple\, easy to implement as a preproc
 essing step (10 lines of Perl!) and outperforms st
 ate-of-the-art approaches on a range of datasets. 
  The technique comes with several simple theoretic
 al guarantees.  Moreover\, it is trivially extende
 d to a multi-domain adaptation problem\, where one
  has data from a variety of different domains. 
LOCATION:GS15\, Computer Laboratory
CONTACT:Diarmuid Ó Séaghdha
END:VEVENT
END:VCALENDAR