Skip to main content

Table 2 Performance (F1 score) of BERT models on the ChemProt, DDI, and PPI datasets

From: Investigation of improving the pre-training and fine-tuning of BERT model for biomedical relation extraction

Model

PPI

DDI

ChemProt

BioBERT

81.0

79.0

75.3

SciBERT

78.8

78.7

74.4

BlueBERT

71.9

76.8

71.2