SynGEC
Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing3 results
- Recall· 2022-10-22SOTA49best: 53.8 (Unsupervised GEC + cLang8)
- F0.5· 2022-10-2267.6best: 72.8 (Ensembles of best 7 models + GRECO + GTP-rerank)
- Precision· 2022-10-2274.7best: 83.9 (Ensembles of best 7 models + GRECO + GTP-rerank)