Table 4 Optimal hyperparameter settings for the model.
From: Chinese medical named entity recognition integrating adversarial training and feature enhancement
Parameter name | Value | Parameter name | Value |
|---|---|---|---|
embedding_dim | 128 | batch_size | 32 |
hidden_dim | 128 | drop_out | 0.3 |
max_sequence_length | 256 | learning_rate | 1e-3 |
epoch | 60 | optimizer | Adam |
