Dialogue Evaluation on EmpatheticDialogues
0.404Spearman CorrelationMDD-C
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MDD-C2021.12 | 0.404 | — | — | — | |
| MDD-CM2021.12 | 0.404 | — | — | — | |
| DEB2021.12 | 0.395 | — | — | — | |
| QuantiDCE2021.06 | 0.393 | 0.412 | 0.274 | 0.36 | |
| MDD-S2021.12 | 0.374 | — | — | — | |
| MDD-T2021.12 | 0.345 | — | — | — | |
| GRADEtraining_dataset=DailyDialog++2021.06 | 0.344 | 0.35 | 0.243 | 0.312 | |
| GRADE2021.12 | 0.297 | — | — | — | |
| USR2021.12 | 0.255 | — | — | — | |
| USL-H2021.12 | 0.235 | — | — | — | |
| BLEURTfine-tuned=true2021.06 | 0.192 | 0.203 | 0.13 | 0.175 | |
| uBERT-R2021.12 | 0.148 | — | — | — | |
| D-score2021.12 | 0.087 | — | — | — | |
| METEOR2021.06 | 0.055 | 0.118 | 0.04 | 0.071 | |
| BERTScore2021.06 | 0.033 | 0.046 | 0.021 | 0.033 | |
| ADEMtraining_dataset=DailyDialog++2021.06 | 0.009 | 0.007 | 0.04 | 0.019 | |
| BLEU2021.06 | 0.002 | -0.051 | 0.005 | -0.015 | |
| ROUGE2021.06 | -0.013 | 0.029 | -0.01 | 0.002 | |
| BERT-RUBERtraining_dataset=DailyDialog++2021.06 | -0.04 | -0.022 | -0.029 | -0.03 |