| Paper | Code | BLEU | MultiWOZ (Inform) | MultiWOZ (Success) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection | ✓ Link | 20.01 | 95.30 | 86.20 | GALAXY | 2021-11-29 |
| A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning | ✓ Link | 18.3 | 78.1 | 67.1 | LABES-S2S | 2020-09-17 |
| AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models | ✓ Link | 17.2 | 91.4 | 72.9 | AuGPT | 2021-02-09 |
| A Simple Language Model for Task-Oriented Dialogue | ✓ Link | 15.2 | 85.0 | 70.5 | SimpleTOD | 2020-05-02 |