Table 1 Data used in prior state-of-the-art studies compared to ours (BioALBERT)
From: Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT
Training corpus | BioBERT [13] | SciBERT [11] | BLUE [12] | PubMedBERT [14] | KeBioLM [15] | BioALBERT |
|---|---|---|---|---|---|---|
General | \(\checkmark\) | \(\times\) | \(\checkmark\) | \(\times\) | \(\times\) | \(\checkmark\) |
PMC | \(\checkmark\) | \(\times\) | \(\times\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) |
PubMed | \(\checkmark\) | \(\times\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) |
Clinical notes | \(\times\) | \(\times\) | \(\checkmark\) | \(\times\) | \(\times\) | \(\checkmark\) |