PubMedBERT

Reported on 3 benchmarks across 2 tasks · 2 papers · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Relation ExtractiononBioRED
F1· 2022-04-08
72.9
SOTA
BioRED: A Rich Biomedical Relation Extraction Dataset arXiv:2204.04263
Relation ExtractiononBioRED
F1· 2022-04-08
58.9
best: 72.9
BioRED: A Rich Biomedical Relation Extraction Dataset arXiv:2204.04263

Medical2 results

Information ExtractiononDDI extraction 2013 corpus
F1· 2020-07-31
0.8236
best: 0.8408 (DESC+MOL+SciBERT)
SOTA
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing arXiv:2007.15779
Information ExtractiononDDI extraction 2013 corpus
Micro F1· 2020-07-31
82.36
best: 84.08 (DESC+MOL+SciBERT)
SOTA
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing arXiv:2007.15779