Unsupervised Machine Translation On Wmt2016 1
Metriken
BLEU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | BLEU |
|---|---|
| mass-masked-sequence-to-sequence-pre-training | 35.2 |
| cross-lingual-language-model-pretraining | 34.3 |
| unsupervised-neural-machine-translation-1 | 26.7 |
| unsupervised-neural-machine-translation-with | 26.3 |
| phrase-based-neural-unsupervised-machine | 25.2 |
| language-models-are-few-shot-learners | 40.6 |
| an-effective-approach-to-unsupervised-machine | 34.4 |