Table 6 Test results of the two models with entity auto-correct algorithm
From: A hybrid approach for named entity recognition in Chinese electronic medical record
Approach | Strict index (%) | ||
|---|---|---|---|
P | R | F1 | |
BiLSTM-CRF | 87.66 | 85.72 | 86.68 |
BiLSTM-CRF + algorithm | 88.73 | 86.78 | 87.74 |
Attention-BiLSTM-CRF | 87.75 | 86.77 | 87.26 |
Attention-BiLSTM-CRF + algorithm | 88.72 | 87.71 | 88.21 |