Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data

Open paper
Benchmark Model Rank Results
grammatical-error-correction-on-conll-2014-shared-taskCopy-augmented Model (4 Ensemble +Denoising Autoencoder)#18F0.5: 61.15Precision: 71.57Recall: 38.65
grammatical-error-correction-on-jflegCopy-augmented Model (4 Ensemble +Denoising Autoencoder)#3GLEU: 61.0

Rank counts only results with a code link.