Table 4 Parameter settings.
From: A novel approach for multiclass sentiment analysis on Chinese social media with ERNIE-MCBMA
Parameters | Values |
|---|---|
dimension of the word embedding vector | 768 |
batchsize | 16 |
number of convolutional kernels | 256 |
hidden_size | 768 |
epoch | 3 |
learning_rate | 5e-5 |
dropout | 0.1 |
