Graph Attention Network Encoder +Transformer Decoder

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Adversarial1 result

Text GenerationonXAlign
BLEU4· 2022-02-01
18.3
best: 29.27 (Fact-aware embedding with mT5)
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages arXiv:2202.00291

Natural Language Processing1 result

Data-to-Text GenerationonXAlign
BLEU4· 2022-02-01
18.3
best: 29.27 (Fact-aware embedding with mT5)
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages arXiv:2202.00291