Human Evaluation of Dialogue Systems on MultiWOZ 2.0 (test)
1.92UnderstandingReference
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Reference2021.09 | 1.92 | 2 | 1.93 | 1.98 | |
| PPTOD_base2021.09 | 1.86 | 1.51 | 1.83 | 1.99 | |
| SOLOIST2021.09 | 1.78 | 1.29 | 1.64 | 1.97 |
| Method | Links | ||||
|---|---|---|---|---|---|
| Reference2021.09 | 1.92 | 2 | 1.93 | 1.98 | |
| PPTOD_base2021.09 | 1.86 | 1.51 | 1.83 | 1.99 | |
| SOLOIST2021.09 | 1.78 | 1.29 | 1.64 | 1.97 |