Identifying Abbreviations in Biological Literature Based on Reverse Text Alignment

The number of biomedical literatures is growing rapidly, and bioinformatics literature mining is becoming essential. The identification of abbreviations in literatures is important for all text mining tools. In the paper, an abbreviation recognition algorithm based on reverse text alignment is proposed and it is easy to be implemented and has fast running time. The algorithm achieves 91 % precision and 93 % recall on the gold standard corpus “Medstract” and 96 % precision and 84 % recall on the larger test data that includes 128 full text literatures.