Skip to main content

Table 1 Model parameter settings

From: Named entity recognition of Chinese electronic medical records based on a hybrid neural network and medical MC-BERT

Parameters

Value

LSTM vector dimension

100

Text batch size

32

Learning rate

5e−5

Maximum sentence length

128

Dropout

0.9

Training batch

50

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us