Machine Translation on newstest En-Ru 2014 (test)
29.37BLEUBase Character-level NMT (Row l)
Evaluation results
| Method | Links | |
|---|---|---|
| Base Character-level NMT (Row l)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 29.37 | |
| Base BPE-level NMT (Row k)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 29.26 | |
| Bi-scale Character-level NMT (Row m)Target=Char, Depth=2, Attention=Concatenated, Model=Bi-S, Ensemble=true2016.03 | 29.26 | |
| State-of-the-art Non-Neural ApproachApproach=Non-Neural2016.03 | 28.7 | |
| Base Character-level NMT (Row l)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 26 | |
| Bi-scale Character-level NMT (Row m)Target=Char, Depth=2, Attention=Concatenated, Model=Bi-S, Ensemble=false2016.03 | 25.59 | |
| Base BPE-level NMT (Row k)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 25.3 |