Copy-augmented Model (4 Ensemble +Denoising Autoencoder)

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Grammatical Error CorrectiononCoNLL-2014 Shared Task
F0.5· 2019-03-01
61.15
best: 72.8 (Ensembles of best 7 models + GRECO + GTP-rerank)
SOTA
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data arXiv:1903.00138
Grammatical Error CorrectiononCoNLL-2014 Shared Task
Precision· 2019-03-01
71.57
best: 83.9 (Ensembles of best 7 models + GRECO + GTP-rerank)
SOTA
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data arXiv:1903.00138
Grammatical Error CorrectiononCoNLL-2014 Shared Task
Recall· 2019-03-01
38.65
best: 53.8 (Unsupervised GEC + cLang8)
SOTA
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data arXiv:1903.00138
Grammatical Error CorrectiononJFLEG
GLEU· 2019-03-01
61
best: 62.1 (VERNet)
Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data arXiv:1903.00138