Stage-wise Fine-tuning for Graph-to-Text Generation
Open paper
Benchmark
Model
Rank
Results
data-to-text-generation-on-webnlg
T5-large + Wiki + Position
#7
BLEU: 66.07
data-to-text-generation-on-webnlg-full
T5-large + Wiki + Position
#3
BLEU: 60.56
Rank counts only results with a code link.