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