Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

1 code implementation • 20 Oct 2023 • Zecheng Tang, Kaifeng Qi, Juntao Li, Min Zhang

By leveraging the augmenting data from the GEC models themselves in the post-training process and introducing regularization data for cycle training, our proposed method can effectively improve the model robustness of well-trained GEC models with only a few more training epochs as an extra cost.

Adversarial Attack Grammatical Error Correction