Hyperparameters used in the experiments.
| Name . | Value . |
|---|---|
| Word Embedding | GloVe (PTB) / fastText (UD) |
| BERT | BERT-Base |
| CNN window size | 3 |
| CNN filters | 30 |
| BiLSTM layers | 2 |
| BiLSTM units | 300 dimensions |
| Optimization | Adam |
| Learning rate | 0.001 |
| Rescaling factor τ | 64 |
| Dropout ratio | {0.1, 0.2, 0.3} |
| Name . | Value . |
|---|---|
| Word Embedding | GloVe (PTB) / fastText (UD) |
| BERT | BERT-Base |
| CNN window size | 3 |
| CNN filters | 30 |
| BiLSTM layers | 2 |
| BiLSTM units | 300 dimensions |
| Optimization | Adam |
| Learning rate | 0.001 |
| Rescaling factor τ | 64 |
| Dropout ratio | {0.1, 0.2, 0.3} |