T5-large + Wiki + Position

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Adversarial2 results

Text GenerationonWebNLG
BLEU· uses extra data· 2021-05-17
66.07
best: 67.32 (Control Prefixes (A1, T5-large))
SOTA
Stage-wise Fine-tuning for Graph-to-Text Generation arXiv:2105.08021
Text GenerationonWebNLG Full
BLEU· uses extra data· 2021-05-17
60.56
best: 62.27 (Control Prefixes (A1, A2, T5-large))
SOTA
Stage-wise Fine-tuning for Graph-to-Text Generation arXiv:2105.08021

Natural Language Processing2 results

Data-to-Text GenerationonWebNLG
BLEU· uses extra data· 2021-05-17
66.07
best: 67.32 (Control Prefixes (A1, T5-large))
SOTA
Stage-wise Fine-tuning for Graph-to-Text Generation arXiv:2105.08021
Data-to-Text GenerationonWebNLG Full
BLEU· uses extra data· 2021-05-17
60.56
best: 62.27 (Control Prefixes (A1, A2, T5-large))
SOTA
Stage-wise Fine-tuning for Graph-to-Text Generation arXiv:2105.08021