Skip to main content

Table 4 Performance (in f-score) for the various pre-trained language models

From: Automatic classification of experimental models in biomedical literature to support searching for alternative methods to animal experiments

Labels

BioBERT

PubMedBERT

SciBERT

BLUE-BERT

invertebrates

0.89

0.95

0.95

0.95

in_vivo

0.88

0.88

0.89

0.83

human

0.82

0.86

0.82

0.73

organs

0.80

0.82

0.82

0.71

primary_cells

0.67

0.75

0.73

0.67

immortal_cell_lines

0.91

0.83

0.80

0.89

in_silico

0.67

0.75

0.75

0.86

others

0.70

0.78

0.67

0.76

All (average)

0.79

0.83

0.80

0.80