Machine Translation On Wmt 2017 Latvian
Metrics
BLEU
Results
Performance results of various models on this benchmark
Model Name | BLEU | Paper Title | Repository |
|---|---|---|---|
| Transformer trained on highly filtered data | 24.37 | Impact of Corpora Quality on Neural Machine Translation | |
| mLSTM with factored data | 20.80 | - | - |
| Attention-based Hybrid NMT combination | 14.83 | Confidence through Attention | |
| RNN | - | Debugging Neural Machine Translations |
0 of 4 row(s) selected.