Text Mining support to curation teams: a pipeline of modules for text processing


Dietrich Rebholz-Schuhmann
(European Bioinformatics Institute, EMBL-EBI)

Curation teams have special demands on text mining solutions.They have to integrate large sets of controlled vocabularies, should process any type of text and should be adaptable to the needs of individual teams. The Rebholz group has developed a set of information extraction modules that can be combined to a text processing pipeline. The presentation will show examples of ongoing work.