CGE-LW

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

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 GenerationonAGENDA
BLEU· 2020-01-29
18.01
best: 25.66 (BART-large+ STA)
SOTA
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs arXiv:2001.11003
Graph-to-SequenceonWebNLG
BLEU· 2020-01-29
63.69
SOTA
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs arXiv:2001.11003
KG-to-Text GenerationonAGENDA
BLEU· 2020-01-29
18.01
best: 25.66 (BART-large+ STA)
SOTA
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs arXiv:2001.11003

Adversarial1 result

Text GenerationonAGENDA
BLEU· 2020-01-29
18.01
best: 25.66 (BART-large+ STA)
SOTA
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs arXiv:2001.11003