Table 1 Overall evaluation results (we report percentages) on the original corpus ( Saha et al. 2013 )
From: Biomedical named entity extraction: some issues of corpus compatibilities
Corpus | Model | Recall | Precision | F-measure |
|---|---|---|---|---|
GENIA | Best individual classifier | 73.10 | 76.78 | 74.90 |
SOO based ensemble | 74.17 | 77.87 | 75.97 | |
AIMeD | Best individual classifier | 94.56 | 92.66 | 93.60 |
SOO based ensemble | 95.65 | 94.23 | 94.93 | |
GENETAG | Best individual classifier | 95.35 | 95.31 | 95.33 |
SOO based ensemble | 95.99 | 95.81 | 95.90 |