Task-oriented Dialogue on FewShotWeather seen structures (test)
74.43BLEUFull Data Baseline
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Full Data BaselineTrain split=16,8162021.10 | 74.43 | 99.55 | |
| BLEURT self-trainingPseudo-response selection strategy=BLEURT, Train split=1shot-10002021.10 | 73.82 | 98.48 | |
| Vanilla self-trainingPseudo-response selection strategy=Vanilla, Train split=1shot-10002021.10 | 73.38 | 96.16 | |
| Vanilla self-trainingPseudo-response selection strategy=Vanilla, Train split=1shot-7502021.10 | 73.02 | 96.61 | |
| T5-smallPseudo-response selection strategy=None, Train split=1shot-10002021.10 | 72.89 | 95.18 | |
| BLEURT self-trainingPseudo-response selection strategy=BLEURT, Train split=1shot-7502021.10 | 72 | 97.23 | |
| T5-smallPseudo-response selection strategy=None, Train split=1shot-7502021.10 | 69.81 | 92.86 | |
| BLEURT self-trainingPseudo-response selection strategy=BLEURT, Train split=1shot-2502021.10 | 69.59 | 84.12 | |
| T5-smallPseudo-response selection strategy=None, Train split=1shot-5002021.10 | 69.4 | 83.59 | |
| Vanilla self-trainingPseudo-response selection strategy=Vanilla, Train split=1shot-2502021.10 | 69.25 | 73.77 | |
| T5-smallPseudo-response selection strategy=None, Train split=1shot-2502021.10 | 69.16 | 73.68 | |
| Vanilla self-trainingPseudo-response selection strategy=Vanilla, Train split=1shot-5002021.10 | 68.75 | 89.21 | |
| BLEURT self-trainingPseudo-response selection strategy=BLEURT, Train split=1shot-5002021.10 | 68.19 | 93.4 |