Skip to main content

Table 2 Comparison of the biomedical datasets in prior studies and ours (BioALBERT)

From: Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT

Datasets

BioBERT [13]

SciBERT[11]

BLUE [12]

PubMedBERT [14]

KeBioLM [15]

BioALBERT

Share/Clefe [17]

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

BC5CDR (disease) [18]

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

BC5CDR (chemical) [18]

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

JNLPBA [19]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

LINNAEUS [20]

\(\checkmark\)

\(\times\)

\(\times\)

\(\times\)

\(\times\)

\(\checkmark\)

NCBI (disease) [21]

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

Species-800 (S800) [22]

\(\checkmark\)

\(\times\)

\(\times\)

\(\times\)

\(\times\)

\(\checkmark\)

BC2GM [23]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

DDI [24]

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

ChemProt [7]

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

i2b2 [25]

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

Euadr [26]

\(\checkmark\)

\(\times\)

\(\times\)

\(\times\)

\(\times\)

\(\checkmark\)

GAD [27]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

BIOSSES [28]

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

MedSTS [29]

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

MedNLI [30]

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

HoC [31]

\(\times\)

\(\times\)

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

BioASQ 4b [32]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

BioASQ 5b [32]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

BioASQ 6b [32]

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\checkmark\)