Machine Translation on en-pt stylized (test)
2.7Score (E)Baseline
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BaselineArchitecture=Transformer-base, Encoder layers=6, Decoder layers=6, Attention layer size=512, Batch size=4096 tokens, Optimizer=Adam, Label smoothing=0.12022.12 | 2.7 | 2.8 | |
| StyleAPArchitecture=Transformer-base, Encoder layers=6, Decoder layers=6, Attention layer size=512, Batch size=4096 tokens, Optimizer=Adam, Label smoothing=0.12022.12 | 2.9 | 2.9 |