Data To Text Generation On Dart
Metrics
BLEU
BLEURT
METEOR
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BLEU | BLEURT | METEOR |
|---|---|---|---|
| factspotter-evaluating-the-factual | 48.47 | 67.49 | 40.74 |
| self-training-from-self-memory-in-data-to | 47.76 | - | - |