Data To Text Generation On Webnlg Full 1
Métriques
BLEU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | BLEU |
|---|---|
| control-prefixes-for-text-generation | 61.94 |
| neural-data-to-text-generation-a-comparison | 51.68 |
| have-your-text-and-use-it-too-end-to-end | 52.9 |
| investigating-pretrained-language-models-for | 59.70 |
| text-to-text-pre-training-for-data-to-text | 57.1 |
| htlm-hyper-text-pre-training-and-prompting-of | 56.3 |
| control-prefixes-for-text-generation | 62.27 |
| stage-wise-fine-tuning-for-graph-to-text | 60.56 |