| Paper | Code | BLEU score | ModelName | ReleaseDate |
|---|---|---|---|---|
| Self-Knowledge Distillation with Progressive Refinement of Targets | ✓ Link | 30.00 | PS-KD | 2020-06-22 |
| Attention Is All You Need | ✓ Link | 28.50 | Transformer | 2017-06-12 |
| Non-Autoregressive Neural Machine Translation | ✓ Link | 28.16 | NAT +FT + NPD | 2017-11-07 |
| Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction | ✓ Link | 27.99 | Pervasive Attention | 2018-08-11 |
| Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement | ✓ Link | 27.01 | Denoising autoencoders (non-autoregressive) | 2018-02-19 |
| Convolutional Sequence to Sequence Learning | ✓ Link | 26.73 | ConvS2S | 2017-05-08 |
| Towards Neural Phrase-based Machine Translation | ✓ Link | 25.36 | NPMT + language model | 2017-06-17 |
| An Actor-Critic Algorithm for Sequence Prediction | ✓ Link | 25.04 | RNNsearch | 2016-07-24 |