| Paper | Code | BLEU | ModelName | ReleaseDate |
|---|---|---|---|---|
| Language Models are Few-Shot Learners | ✓ Link | 39.2 | GPT-3 175B (Few-Shot) | 2020-05-28 |
| MASS: Masked Sequence to Sequence Pre-training for Language Generation | ✓ Link | 34.9 | MASS (6-layer Transformer) | 2019-05-07 |
| An Effective Approach to Unsupervised Machine Translation | ✓ Link | 33.5 | SMT + NMT (tuning and joint refinement) | 2019-02-04 |
| Cross-lingual Language Model Pretraining | ✓ Link | 33.3 | MLM pretraining for encoder and decoder | 2019-01-22 |
| Unsupervised Neural Machine Translation with SMT as Posterior Regularization | ✓ Link | 28.9 | SMT as posterior regularization | 2019-01-14 |
| Phrase-Based & Neural Unsupervised Machine Translation | ✓ Link | 27.7 | PBSMT + NMT | 2018-04-20 |
| Unsupervised Statistical Machine Translation | ✓ Link | 25.9 | SMT | 2018-09-04 |