Figure 7.

PR curves for the length-normalized edit distance (ED) and SoftTFIDF (ST). We plotted recalls on the x-axis and precision on the y-axis. Chemical and non-Chemical correspond to the two datasets, the chemical names and the non-chemical names, respectively.

Yamaguchi et al. BMC Genomics 2012 13(Suppl 3):S8   doi:10.1186/1471-2164-13-S3-S8