Table 7.
Spearman rank correlation coefficient between automatic metrics and human ratings for the text generated by TESLEA.
| Metric | Informativeness | Fluency | Factuality | Coherence | Adequacy |
| ROUGE-1 | 0.18a | –0.04 | –0.01 | –0.05 | 0.06 |
| ROUGE-2 | 0.08 | –0.01 | –0.05 | –0.04 | 0.05 |
| SARI | 0.09 | –0.66 | –0.13 | –0.01 | 0.01 |
| BARTScore | 0.08 | 0.32a | 0.38a | 0.22a | 0.07a |
aBest result.