Atlas
Sign in
Models / bio-nlp / sapbert-from-roberta-base-biomedical-clinical-es / benchmarks

bio-nlp/sapbert-from-roberta-base-biomedical-clinical-es

Visibility: PUBLIC
Model cardFilesBenchmarks
Group by

BC5CDR chemical NER bio-nlp/bc5cdr-chemical-ner

Drawn from: bc5cdr

atlas-n100-v1

Metric Value 95% CI n Rank Best in catalogue Source Overlap Board
Chemical entity F1 (token probe) ↑ higher is better · probe 0.821 [0.784, 0.859] 100 10 / 16 0.889 reproduced none declared Board
Chemical entity precision (token probe) ↑ higher is better · probe 0.819 [0.765, 0.871] 100 10 / 16 0.870 reproduced none declared Board
Chemical entity recall (token probe) ↑ higher is better · probe 0.824 [0.785, 0.864] 100 10 / 16 0.914 reproduced none declared Board

Clinical entity recognition (MACCROBAT) bio-nlp/clinical-entity-recognition

Drawn from: MACCROBAT_biomedical_ner

atlas-n100-v1

Metric Value 95% CI n Rank Best in catalogue Source Overlap Board
Entity F1, 3 types (token probe) ↑ higher is better · probe 0.479 [0.417, 0.538] 100 12 / 16 0.724 reproduced none declared Board
Entity precision, 3 types (token probe) ↑ higher is better · probe 0.459 [0.399, 0.520] 100 10 / 16 0.709 reproduced none declared Board
Entity recall, 3 types (token probe) ↑ higher is better · probe 0.500 [0.425, 0.567] 100 12 / 16 0.739 reproduced none declared Board
Entity macro F1, 3 types (token probe) ↑ higher is better · probe · secondary 0.479 [0.412, 0.537] 100 — 0.728 reproduced none declared Board

PubMedQA accuracy bio-nlp/pubmedqa-accuracy

Drawn from: PubMedQA

atlas-full-v1

Metric Value 95% CI n Rank Best in catalogue Source Overlap Board
Accuracy (logistic probe) ↑ higher is better · probe 0.504 [0.468, 0.540] 500 16 / 17 0.576 reproduced none declared Board
Macro F1 (logistic probe) ↑ higher is better · probe 0.341 [0.307, 0.378] 500 16 / 17 0.444 reproduced none declared Board

Spanish occupation entity recognition (ProfNER) bio-nlp/spanish-occupation-entity-recognition

Drawn from: ProfNER_corpus_NER

atlas-n100-v1

Metric Value 95% CI n Rank Best in catalogue Source Overlap Board
Entity F1, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe 0.575 [0.357, 0.760] 100 3 / 16 0.630 reproduced none declared Board
Entity precision, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe 0.700 [0.458, 0.897] 100 5 / 16 1.000 reproduced none declared Board
Entity recall, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe 0.488 [0.273, 0.700] 100 3 / 16 0.535 reproduced none declared Board
Entity macro F1, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe · secondary 0.300 [0.207, 0.755] 100 — 0.329 reproduced none declared Board