Towards Minimal Supervision BERT-based Grammar Error Correction

Abstract

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.

Cited by in corpus (1)

• Recent Trends in the Use of Deep Learning Models for Grammar Error Handling