Models / bio-nlp / bio-clinicalbert / benchmarks

bio-nlp/bio-clinicalbert

Visibility: PUBLIC

Model card FilesBenchmarks

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	0.829	[0.792, 0.865]	100	9 / 16	0.889	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Chemical entity precision (token probe) ↑ higher is better · probe	0.829	[0.782, 0.877]	100	8 / 16	0.870	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Chemical entity recall (token probe) ↑ higher is better · probe	0.829	[0.780, 0.871]	100	9 / 16	0.914	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	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	[0.413, 0.540]	100	11 / 16	0.724	reproduced	overlap Train/test overlap declared by the evaluator: PubMed Central full text	Board
Entity precision, 3 types (token probe) ↑ higher is better · probe	0.444	[0.378, 0.509]	100	13 / 16	0.709	reproduced	overlap Train/test overlap declared by the evaluator: PubMed Central full text	Board
Entity recall, 3 types (token probe) ↑ higher is better · probe	0.521	[0.449, 0.584]	100	8 / 16	0.739	reproduced	overlap Train/test overlap declared by the evaluator: PubMed Central full text	Board
Entity macro F1, 3 types (token probe) ↑ higher is better · probe · secondary	0.472	[0.397, 0.535]	100	—	0.728	reproduced	overlap Train/test overlap declared by the evaluator: PubMed Central full text	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	0.512	[0.476, 0.550]	500	15 / 17	0.576	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Macro F1 (logistic probe) ↑ higher is better · probe	0.351	[0.314, 0.395]	500	15 / 17	0.444	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	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	0.045	[0.000, 0.125]	100	13 / 16	0.630	reproduced	none declared	Board
Entity precision, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe	1.000 best	[0.000, 1.000]	100	1 / 16	1.000	reproduced	none declared	Board
Entity recall, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe	0.023	[0.000, 0.067]	100	13 / 16	0.535	reproduced	none declared	Board
Entity macro F1, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe · secondary	0.024	[0.000, 0.111]	100	—	0.329	reproduced	none declared	Board