GCN + feat

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

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

Adversarial1 result

Text GenerationonSR11Deep
BLEU· 2018-10-23
0.666
best: 80.49 (Transition based Deep Input Linearization)
SOTA
Deep Graph Convolutional Encoders for Structured Data to Text Generation arXiv:1810.09995

Natural Language Processing1 result

Data-to-Text GenerationonSR11Deep
BLEU· 2018-10-23
0.666
best: 80.49 (Transition based Deep Input Linearization)
SOTA
Deep Graph Convolutional Encoders for Structured Data to Text Generation arXiv:1810.09995