Chinese grammatical error correction based on knowledge distillation
This work addresses robustness issues in Chinese grammatical error correction for NLP applications, but it is incremental as it applies an existing method to a specific domain.
The paper tackled the poor robustness and large parameter size of Chinese grammatical error correction models by using knowledge distillation to compress parameters and improve anti-attack ability, achieving optimal results on an attack test set with significantly enhanced robustness.
In view of the poor robustness of existing Chinese grammatical error correction models on attack test sets and large model parameters, this paper uses the method of knowledge distillation to compress model parameters and improve the anti-attack ability of the model. In terms of data, the attack test set is constructed by integrating the disturbance into the standard evaluation data set, and the model robustness is evaluated by the attack test set. The experimental results show that the distilled small model can ensure the performance and improve the training speed under the condition of reducing the number of model parameters, and achieve the optimal effect on the attack test set, and the robustness is significantly improved. Code is available at https://github.com/Richard88888/KD-CGEC.