CBR-Tagger: a case-based reasoning approach to the gene/protein mention problem

This work proposes a case-based classifier to tackle the gene/protein mention problem in biomedical literature. The so called gene mention problem consists of the recognition of gene and protein entities in scientific texts. A classification process aiming at deciding if a term is a gene mention or not is carried out for each word in the text. It is based on the selection of the best or most similar case in a base of known and unknown cases. The approach was evaluated on several datasets for different organisms and results show the suitability of this approach for the gene mention problem.