Models / bio-nlp / biomedvlp-cxr-bert-specialized / benchmarks

bio-nlp/biomedvlp-cxr-bert-specialized

Visibility: PUBLIC

Model card FilesBenchmarks

Group by

bc5cdr bio-nlp/bc5cdr

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	0.889 best	[0.857, 0.921]	100	1 / 16	0.889	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Chemical entity precision (token probe) ↑ higher is better · probe	0.865	[0.820, 0.912]	100	2 / 16	0.870	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Chemical entity recall (token probe) ↑ higher is better · probe	0.914 best	[0.884, 0.941]	100	1 / 16	0.914	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board

MACCROBAT_biomedical_ner bio-nlp/maccrobat-biomedical-ner

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	0.562	[0.488, 0.627]	100	2 / 16	0.724	reproduced	unknown	Board
Entity precision, 3 types (token probe) ↑ higher is better · probe	0.533	[0.459, 0.608]	100	2 / 16	0.709	reproduced	unknown	Board
Entity recall, 3 types (token probe) ↑ higher is better · probe	0.594	[0.514, 0.664]	100	2 / 16	0.739	reproduced	unknown	Board
Entity macro F1, 3 types (token probe) ↑ higher is better · probe · secondary	0.568	[0.480, 0.636]	100	—	0.728	reproduced	unknown	Board

ProfNER_corpus_NER bio-nlp/profner-corpus-ner

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	0.231	[0.048, 0.400]	100	10 / 16	0.630	reproduced	none declared	Board
Entity precision, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe	0.667	[0.332, 1.000]	100	6 / 16	1.000	reproduced	none declared	Board
Entity recall, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe	0.140	[0.026, 0.277]	100	10 / 16	0.535	reproduced	none declared	Board
Entity macro F1, PROFESION + SITUACION_LABORAL (token probe) ↑ higher is better · probe · secondary	0.122	[0.027, 0.381]	100	—	0.329	reproduced	none declared	Board

PubMedQA bio-nlp/pubmedqa

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	0.564	[0.524, 0.600]	500	2 / 17	0.576	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board
Macro F1 (logistic probe) ↑ higher is better · probe	0.405	[0.364, 0.447]	500	4 / 17	0.444	reproduced	overlap Train/test overlap declared by the evaluator: PubMed abstracts	Board