Towards Minimal Supervision BERT-Based Grammar Error Correction (Student 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 datalimited 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.

Authors

• Yiyuan Li
• Antonios Anastasopoulos
• Alan W. Black

Keywords

No keywords are indexed for this paper.