Table 6 NER results of BERT on the diagnosis dataset evaluated with BERT labels and WP label
From: Korean clinical entity recognition from diagnosis text using BERT
| Â | BERT labels | WP labels | ||
|---|---|---|---|---|
| Â | macro-avg | micro-avg | macro-avg | micro-avg |
Precision | 0.72 | 0.83 | 0.70 | 0.82 |
Recall | 0.72 | 0.84 | 0.73 | 0.84 |
F1 | 0.72 | 0.84 | 0.72 | 0.83 |