Table 2 Performance of PICO sentence classification by BERT with different pre-trained weights on the test set
From: PICO entity extraction for preclinical animal literature
| Â | F1 | Recall | Precision |
|---|---|---|---|
BERT-base | 80.6 | 81.4 | 82.1 |
BioBERT | 84.3 | 81.0 | 90.0 |
PubMedBERT-abs | 85.4 | 88.4 | 85.0 |
PubMedBERT-full | 84.2 | 87.1 | 83.8 |