Machine Translation on newstest En-De 2013 (dev)
23.49BLEUBase BPE-level NMT (Row b)
Evaluation results
| Method | Links | |
|---|---|---|
| Base BPE-level NMT (Row b)Target=BPE, Depth=2, Attention=hL, Model=Base, Ensemble=true2016.03 | 23.49 | |
| Base BPE-level NMT (Row c)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 23.14 | |
| Base Character-level NMT (Row e)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 23.05 | |
| Base BPE-level NMT (Row c)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 21.57 | |
| Base Character-level NMT (Row e)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 21.39 | |
| Base BPE-level NMT (Row b)Target=BPE, Depth=2, Attention=hL, Model=Base, Ensemble=false2016.03 | 21.28 | |
| Base BPE-level NMT (Row a)Target=BPE, Depth=1, Attention=h1, Model=Base, Ensemble=false2016.03 | 20.78 | |
| Bi-scale Character-level NMT (Row f)Target=Char, Depth=2, Attention=hL, Model=Bi-S, Ensemble=false2016.03 | 20.78 | |
| Base Character-level NMT (Row d)Target=Char, Depth=2, Attention=hL, Model=Base, Ensemble=false2016.03 | 20.31 | |
| Bi-scale Character-level NMT (Row g)Target=Char, Depth=2, Attention=Concatenated, Model=Bi-S, Ensemble=false2016.03 | 20.08 |