Table 5 Performances of methods on contiguous and discontiguous clinical entity under “strict” criterion on ICRC_CNER
From: Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF
Method | Contiguous entity (%) | Discontiguous entity (%) | ||||
|---|---|---|---|---|---|---|
Precision | Recall | F1-score | Precision | Recall | F1-score | |
CRF | 83.52 | 84.35 | 83.93 | 82.73 | 58.26 | 68.37 |
LSTM-CRF | 83.35 | 87.35 | 85.30 | 78.70 | 63.62 | 70.36 |
Our method | 83.57 | 87.75 | 85.61 | 77.17 | 65.76 | 71.01 |