BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Event Extraction from Biomedical Texts by Trimming Dependency Grap
 hs - Ekaterina Buyko - JULIE Lab\, Friedrich-Schiller-Universität Jena
DTSTART:20101021T120000Z
DTEND:20101021T130000Z
UID:TALK27520@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:In the biomedical information extraction community\, the focus
  has largely been on binary protein-protein (PPIs) interactions\, for a lo
 ng time. Quite recently\, text analytics have been developed dealing with 
 bio-event extraction. In essence\, this means that the general PPI problem
  is broken down into much more specific subtasks. A bio-event is then defi
 ned as a change of the biological state\, the properties\, or the location
  of a bio-molecule. The most recent BioNLP 2009 Shared Task on Event Extra
 ction required to determine\, from a sample of Medline abstracts\, all men
 tioned events of nine bio-molecular interaction types\, including\, e.g.\,
  Binding\, Transcription and Regulation events. Interestingly\, the three 
 top-performing systems of that competition all rely on dependency graphs f
 or solving this event extraction task. However\, while the UTurku and Conc
 ordU systems exploit Stanford grammatical relations\, the JulieLab system 
 (U Jena) uses CoNLL dependencies. Obviously\, the question turns up as to 
 what extent the performance of these systems depends on proper choices of 
 the available parsers and dependency output representations.\n\nI will dis
 cuss the Shared Task solution of the JulieLab system which relies on 'trim
 ming' dependency graphs by syntactic simplification and semantic enrichmen
 t operations. Furthermore\, the role of different representation formats o
 f dependency graphs in the event extraction task (basically\, Stanford vs.
  CoNLL encodings) will be considered. Given JulieLab's high-performance ev
 ent extraction system and taking considerations of its methodological unde
 rpinnings into account\, we currently expand our approach into more real-l
 ife information extraction scenarios\, e.g.\, the support of human databas
 e curators.
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR