NCBI_BERT(large) (P)

Reported on 5 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Natural Language Processing3 results

Text ClassificationonHOC
F1· 2019-06-13
87.3
best: 88.1 (BioLinkBERT (large))
SOTA
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets arXiv:1906.05474
Document ClassificationonHOC
F1· 2019-06-13
87.3
best: 88.1 (BioLinkBERT (large))
SOTA
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets arXiv:1906.05474
Relation ExtractiononChemProt
F1· 2019-06-13
74.4
best: 83.64 (SciBert (Finetune))
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets arXiv:1906.05474

Medical1 result

Medical Relation ExtractiononDDI extraction 2013 corpus
F1· 2019-06-13
79.9
best: 83.35 (BioLinkBERT (large))
SOTA
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets arXiv:1906.05474

Methodology1 result

ClassificationonHOC
F1· 2019-06-13
87.3
best: 88.1 (BioLinkBERT (large))
SOTA
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets arXiv:1906.05474