Skip to main content

Advertisement

Table 7 Performance of removing different techniques

From: Constructing a Chinese electronic medical record corpus for named entity recognition on resident admit notes

  Precision Recall F
Best 90.76 91.4 91.08
No Dropout 89.85 290.12 89.98
No Attention 90.37 91.15 90.76
No Char Embeddings 84.61 84.81 84.71
LSTM for Char Embeddings 90.64 91.38 91.01