BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semantics in broad-coverage natural language processing - Ann Cope
 stake\,  Computer Laboratory\, University of Cambridge
DTSTART:20061018T131500Z
DTEND:20061018T141500Z
UID:TALK5369@talks.cam.ac.uk
CONTACT:Timothy G. Griffin
DESCRIPTION:Much work on natural language processing (NLP) in the 1970s an
 d 1980s\nconcentrated on natural language interfaces.  Input was analysed 
 to\nproduce a detailed meaning representation that could be interpreted by
 \nthe underlying application\, generally as a database query or as a\ncomm
 and.  This was tractable because of the constraints imposed by the\nvery l
 imited domains of the applications\, but scaling to systems which\nprocess
  more general language proved extremely difficult.  Later NLP\nwork develo
 ped techniques which were broad-coverage and usable for\nlarge scale proce
 ssing\, but too shallow to support the extraction of\ndetailed meaning rep
 resentations.  I'll explain some of the issues\nthat make associating sema
 ntics with arbitrary natural language text a\nmajor challenge for computat
 ional linguistics and the progress that is\nnow being made towards that go
 al.  I'll describe some application\nareas in which broad-coverage semanti
 cs is now being used\,\nconcentrating on text mining for eScience.
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR