Skip to main content

Table 5 hyper parameters

From: MLM-based typographical error correction of unstructured medical texts for named entity recognition

Hyperparameter

Value

Learning rate

3e-5

Epochs

3

Max sequence length

178

Batch size

16

Optimizer

Adam

Activation function

Softmax

  1. Information of fine-tuning process using pre-trained BERT, such as learning rate, epochs, max sequence length, batch size, optimizer, and activation function
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us