End To End Dialogue Modelling On Multiwoz 2 0
평가 지표
BLEU
MultiWOZ (Inform)
MultiWOZ (Success)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | BLEU | MultiWOZ (Inform) | MultiWOZ (Success) | Paper Title | Repository |
|---|---|---|---|---|---|
| GALAXY | 20.5 | 94.4 | 85.3 | GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection | |
| Noisy Channel Model | 20.6 | 86.9 | 76.2 | Pretraining the Noisy Channel Model for Task-Oriented Dialogue | - |
| DAMD | 18.6 | 76.3 | 60.4 | Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context | |
| SOLOIST | 16.5 | 85.5 | 72.9 | SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching | |
| AuGPT | 17.2 | 90.2 | 75.5 | AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models | |
| SimpleTOD | 15.0 | 84.4 | 70.1 | A Simple Language Model for Task-Oriented Dialogue |
0 of 6 row(s) selected.