Command Palette
Search for a command to run...
Unsupervised Machine Translation On Wmt2016
Métriques
BLEU
Résultats
Résultats de performance de divers modèles sur ce benchmark
| Paper Title | ||
|---|---|---|
| GPT-3 175B (Few-Shot) | 29.7 | Language Models are Few-Shot Learners |
| MASS (6-layer Transformer) | 28.3 | MASS: Masked Sequence to Sequence Pre-training for Language Generation |
| SMT + NMT (tuning and joint refinement) | 26.9 | An Effective Approach to Unsupervised Machine Translation |
| MLM pretraining for encoder and decoder | 26.4 | Cross-lingual Language Model Pretraining |
| SMT as posterior regularization | 21.7 | Unsupervised Neural Machine Translation with SMT as Posterior Regularization |
| PBSMT + NMT | 20.2 | Phrase-Based & Neural Unsupervised Machine Translation |
| Synthetic bilingual data init | 20.0 | Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation |
0 of 7 row(s) selected.