Prev
The CALBC Challenge is now opened (first cycle).
Participation is open to any team that is either willing to submit annotations obtained with their own named entity recognition or concept identification system or that wants to reproduce at a large scale the annotations from the annotated corpus.
This challenge aims at creating a broadly-scoped and diversely annotated biomedical text corpus (150,000 Medline abstracts on immunology annotated with different semantic groups) by automatically integrating the annotations from many different named entity recognition and concept identification systems. The final goal will be to come up with an automatically harmonized silver standard, rather than a manually generated gold standard.
Participants will receive an assessment of their results against the silver standard corpus (SSC) through a fully automated analysis. They can submit through an automatic submission site to receive feedback on their annotations. Submissions can be made and assessments will be provided on a regular basis.
Submitted annotations will be used to generate a revised version of the SSC after the submission period is closed.
There will be a workshop in April 2010 at the EBI, Cambridge, U.K. to discuss the challenge outcome. In the second half of 2010, the second round of the challenge will open.
Participants have to sign up to the CALBC mailing list for the challenge: challenge@calbc.eu. Participants who want to sign up to the mailing list should send a request to public@calbc.eu and will receive login details thereafter. After login, you can access the annotated corpus.
For further information see www.calbc.eu/
Dietrich Rebholz-Schuhmann
European Bioinformatics Institute, Hinxton, U.K
Kerstin Hornbostel
Jena University Language & Information Engineering (JULIE) Lab, Germany