Towards Minimal Supervision BERT-Based Grammar Error Correction (Student Abstract)

Authors

  • Yiyuan Li Carnegie Mellon University
  • Antonios Anastasopoulos Carnegie Mellon University
  • Alan W. Black Carnegie Mellon University

DOI:

https://doi.org/10.1609/aaai.v34i10.7202

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.

AAAI-20 Proceedings Cover

Downloads

Published

2020-04-03

How to Cite

Li, Y., Anastasopoulos, A., & Black, A. W. (2020). Towards Minimal Supervision BERT-Based Grammar Error Correction (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13859-13860. https://doi.org/10.1609/aaai.v34i10.7202

Issue

Vol. 34 No. 10: Issue 10: AAAI-20 Student Tracks

Section

Student Abstract Track