Abstract
There has been an increased interest in low-resource approaches to automatic grammatical error correction. We introduce Minimally-Augmented Grammatical Error Correction (MAGEC) that does not require any error-labelled data. Our unsupervised approach is based on a simple but effective synthetic error generation method based on confusion sets from inverted spell-checkers. In low-resource settings, we outperform the current state-of-the-art results for German and Russian GEC tasks by a large margin without using any real error-annotated training data. When combined with labelled data, our method can serve as an efficient pre-training technique- Anthology ID:
- D19-5546
- Volume:
- Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 357–363
- Language:
- URL:
- https://aclanthology.org/D19-5546
- DOI:
- 10.18653/v1/D19-5546
- Cite (ACL):
- Roman Grundkiewicz and Marcin Junczys-Dowmunt. 2019. Minimally-Augmented Grammatical Error Correction. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 357–363, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Minimally-Augmented Grammatical Error Correction (Grundkiewicz & Junczys-Dowmunt, WNUT 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/D19-5546.pdf