Multilingual fine-tuning for Grammatical Error Correction

作者：

Highlights：

• Single model is capable of solving GEC for multiple languages.

• Pre-trained denoising autoencoder is effective in solving multilingual GEC.

• Fine-tuning is sufficient for developing multilingual GEC system.

摘要

•Single model is capable of solving GEC for multiple languages.•Pre-trained denoising autoencoder is effective in solving multilingual GEC.•Fine-tuning is sufficient for developing multilingual GEC system.

论文关键词：Multilingual denoising autoencoder transformer,Sequence-to-sequence,Grammatical error correction

论文评审过程：Received 14 April 2021, Revised 29 December 2021, Accepted 17 March 2022, Available online 6 April 2022, Version of Record 9 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116948