Table 2 Hyperparameter settings for each module in the model.
Parameter | Setting | |
|---|---|---|
BERT Module | Hidden Layer Dimension | 768 |
Number of Attention Heads | 12 | |
Learning Rate | 2e-5 (Adam Optimizer) | |
GCN Module | Hidden Layer Dimension | 768 |
Number of Graph Convolution Layers | 2 | |
Output Dimension per Layer | 32 | |
Activation Function | ReLU | |
Regularization Parameter | L2 Regularization (1e-5) | |
Number of Training Epochs | 100 | |
Batch Size | 32 | |
