Text-to-Text Pre-Training for Data-to-Text Tasks
Open paper
Benchmark
Model
Rank
Results
data-to-text-generation-on-totto
T5-3B
#1
BLEU: 49.5
PARENT: 58.4
data-to-text-generation-on-webnlg
T5-Base
#9
BLEU: 64.7
data-to-text-generation-on-webnlg-full
T5-Large
#5
BLEU: 57.1
Rank counts only results with a code link.