Skip to main content

Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 4 Performances of our CNN-LSTM-Attention model on each category under “strict” criterion

From: Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF

Category ICRC_CNER (%) CCKS2017_CNER (%)
Pre. Rec. F1 Pre. Rec. F1
Disease 82.84 81.67 82.25 85.06 77.22 80.95
Symptom 77.06 76.01 76.53 94.92 96.28 95.60
Test 84.19 89.03 86.55 93.66 93.48 93.57
Treatment 77.53 79.58 78.54 77.63 79.08 83.98
Medication 87.88 89.72 88.79 / / /
Body / / / 86.89 87.36 87.12
  1. Table 2 shows the performances of different methods on CCKS2017_CNER and ICRC_CNER, where the highest measures are in bold (the following sections also use the same way to denote the highest measures)