Table 1.
F1 scores and standard deviations between folds of the 10-fold cross-validation of NER with BERT and 3 science domain-specific derivatives BioBERT, SciBERT and PubMedBERT
| Label class | BERT | BioBERT | SciBERT | PubMedBERT |
|---|---|---|---|---|
| Disease | 0.92 (± 0.03) | 0.95 (± 0.02) | 0.94 (± 0.01) | 0.95 (± 0.02) |
| Drug | 0.93 (± 0.01) | 0.95 (± 0.02) | 0.95 (± 0.01) | 0.95 (± 0.01) |
| Identifier | 0.95 (± 0.02) | 0.97 (± 0.03) | 0.97 (± 0.02) | 0.98 (± 0.01) |
| Methodology | 0.91 (± 0.02) | 0.94 (± 0.01) | 0.93 (± 0.01) | 0.94 (± 0.01) |
| Parameter | 0.81 (± 0.04) | 0.87 (± 0.02) | 0.86 (± 0.03) | 0.87 (± 0.03) |
| Result | 0.96 (± 0.01) | 0.98 (± 0.00) | 0.98 (± 0.00) | 0.98 (± 0.00) |
| Therapy | 0.90 (± 0.03) | 0.93 (± 0.03) | 0.93 (± 0.03) | 0.94 (± 0.02) |
| Weighted Average | 0.92 (± 0.01) | 0.95 (± 0.01) | 0.94 (± 0.01) | 0.95 (± 0.01) |