Machine Translation on newstest En-Fi 2015 (test)
13.48BLEUBase Character-level NMT (Row o)
Evaluation results
| Method | Links | |
|---|---|---|
| Base Character-level NMT (Row o)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 13.48 | |
| Bi-scale Character-level NMT (Row p)Target=Char, Depth=2, Attention=Concatenated, Model=Bi-S, Ensemble=true2016.03 | 13.32 | |
| State-of-the-art Non-Neural ApproachApproach=Non-Neural2016.03 | 12.7 | |
| Base BPE-level NMT (Row n)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=true2016.03 | 11.73 | |
| Base Character-level NMT (Row o)Target=Char, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 10.93 | |
| Bi-scale Character-level NMT (Row p)Target=Char, Depth=2, Attention=Concatenated, Model=Bi-S, Ensemble=false2016.03 | 10.24 | |
| Base BPE-level NMT (Row n)Target=BPE, Depth=2, Attention=Concatenated, Model=Base, Ensemble=false2016.03 | 8.97 |