Table 5 Results for entity recognition in macro multi-class precision, recall, and F1-score
From: Explanatory argumentation in natural language for correct and incorrect medical diagnoses
Model | P | R | F1 |
|---|---|---|---|
BERT | 0.85 | 0.84 | 0.84 |
BioBERT v1.2 | 0.84 | 0.85 | 0.84 |
UmlsBERT | 0.85 | 0.85 | 0.85 |
PubMedBERTbase | 0.83 | 0.84 | 0.83 |
SciBERT cased | 0.85 | 0.85 | 0.85 |
SciBERT uncased | 0.85 | 0.86 | 0.86 |