Skip to main content

Table 7 Impact of the dictionary features on our method

From: Multi-task learning for Chinese clinical named entity recognition with external knowledge

Dataset

Method

Precision

Recall

F-measure

CCKS2017

FT-BERT-Radical

91.69

91.34

91.51

FT-BERT-Radical+Dictionary

91.91

91.78

91.84

FCCd

FT-BERT-Radical

86.95

86.56

86.75

FT-BERT-Radical+Dictionary

87.32

86.79

87.05

  1. The best result is in bold