Skip to main content

Advertisement

Table 3 Effects of the CNN layer and attention layer in our method

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

Method CCKS2017_CNER (%) ICRC_CNER (%)
Precision Recall F1-score Precision Recall F1-score
Our method 90.73 90.49 90.61 82.66 83.99 83.32
w/o CNN 91.11 90.48 90.79 83.72 82.53 83.12
w/o attention 90.61 90.23 90.42 83.16 83.29 83.22
w/o both 90.68 89.67 90.17 82.71 83.30 83.00
  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)