Graformer

Reported on 5 benchmarks across 3 tasks · 1 paper

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

Natural Language Processing3 results

Data-to-Text GenerationonWebNLG
BLEU· 2020-06-16
61.15
best: 67.32 (Control Prefixes (A1, T5-large))
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs arXiv:2006.09242
Data-to-Text GenerationonAGENDA
BLEU· 2020-06-16
17.8
best: 25.66 (BART-large+ STA)
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs arXiv:2006.09242
KG-to-Text GenerationonAGENDA
BLEU· 2020-06-16
17.8
best: 25.66 (BART-large+ STA)
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs arXiv:2006.09242

Adversarial2 results

Text GenerationonWebNLG
BLEU· 2020-06-16
61.15
best: 67.32 (Control Prefixes (A1, T5-large))
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs arXiv:2006.09242
Text GenerationonAGENDA
BLEU· 2020-06-16
17.8
best: 25.66 (BART-large+ STA)
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs arXiv:2006.09242