Current grammatical error correction (GEC) models typically consider the task as sequence generation, which requires large amounts of annotated data and limit the applications in data-limited settings. We try to incorporate contextual information from pre-trained language model to leverage annotation and benefit multilingual scenarios. Results show strong potential of Bidirectional Encoder Representations from Transformers (BERT) in grammatical error correction task.
@article{arxiv.2001.03521,
title = {Towards Minimal Supervision BERT-based Grammar Error Correction},
author = {Yiyuan Li and Antonios Anastasopoulos and Alan W Black},
journal= {arXiv preprint arXiv:2001.03521},
year = {2020}
}