Recognition and normalization of disease mentions in PubMed abstracts

The rapidly increasing number of available PubMed documents calls the need for an automatic approach in the identification and normalization of disease mentions in order to increase the precision and effectivity of information retrieval. We herein describe our team’s participation for the Disease Named Entity Recognition and Normalization subtask under the chemical-disease relations track of the BioCreative V shared task. We developed a CRF-based model using BIESO tagging format to allow automated recognition of disease entities in PubMed abstracts. Recognized disease entities were normalized to MeSH concepts using a dictionary look-up method based on Lucene. Performance is reported using precision, recall and F-measure on three separate runs. Our best run achieved F-measure of 80.74% on disease mention recognition and 67.85 % on disease normalization.