Table To Text Generation On Dart
Métriques
BERT
BLEU
BLEURT
METEOR
Mover
TER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | BERT | BLEU | BLEURT | METEOR | Mover | TER | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| GPT-2-Large (fine-tuning) | 0.94 | 47.0 | 0.4 | 0.39 | 0.51 | 0.46 | HTLM: Hyper-Text Pre-Training and Prompting of Language Models | - |
| HTLM (fine-tuning) | 0.94 | 47.2 | 0.4 | 0.39 | 0.51 | 0.44 | HTLM: Hyper-Text Pre-Training and Prompting of Language Models | - |
0 of 2 row(s) selected.