Kg To Text Generation On Webnlg Unseen
Metrics
BLEU
METEOR
chrF++
Results
Performance results of various models on this benchmark
Comparison Table
Model Name | BLEU | METEOR | chrF++ |
---|---|---|---|
investigating-pretrained-language-models-for | 53.67 | 42.26 | 72.25 |
investigating-pretrained-language-models-for | 43.97 | 38.61 | 66.53 |