SemEHR+WS (rules+BlueBERT)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing2 results

Entity LinkingonRare Diseases Mentions in MIMIC-III (Text-to-UMLS)
F1· 2021-05-05
0.858
best: 0.861 (SemEHR+WS (rules+BlueBERT) with tuning number of training data)
SOTA
Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision arXiv:2105.01995
Entity LinkingonRare Diseases Mentions in MIMIC-III
F1· 2021-05-05
0.702
best: 0.711 (SemEHR+WS (rules+BlueBERT) with tuning number of training data)
SOTA
Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision arXiv:2105.01995