Metric: BLEU score (higher is better)
| # | Model↕ | BLEU score▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PS-KD | 30 | No | Self-Knowledge Distillation with Progressive Ref... | 2020-06-22 | Code |
| 2 | Transformer | 28.5 | No | Attention Is All You Need | 2017-06-12 | Code |
| 3 | NAT +FT + NPD | 28.16 | No | Non-Autoregressive Neural Machine Translation | 2017-11-07 | Code |
| 4 | Pervasive Attention | 27.99 | No | Pervasive Attention: 2D Convolutional Neural Net... | 2018-08-11 | Code |
| 5 | Denoising autoencoders (non-autoregressive) | 27.01 | No | Deterministic Non-Autoregressive Neural Sequence... | 2018-02-19 | Code |
| 6 | ConvS2S | 26.73 | No | Convolutional Sequence to Sequence Learning | 2017-05-08 | Code |
| 7 | NPMT + language model | 25.36 | No | Towards Neural Phrase-based Machine Translation | 2017-06-17 | Code |
| 8 | RNNsearch | 25.04 | No | An Actor-Critic Algorithm for Sequence Prediction | 2016-07-24 | Code |