Abstract
Grammatical Error Correction (GEC) enhances language proficiency and promotes effective communication, but research has primarily centered around English. We propose a simple approach to multilingual and low-resource GEC by exploring the potential of multilingual machine translation (MT) models for error correction. We show that MT models are not only capable of error correction out-of-the-box, but that they can also be fine-tuned to even better correction quality. Results show the effectiveness of this approach, with our multilingual model outperforming similar-sized mT5-based models and even competing favourably with larger models.- Anthology ID:
- 2024.eacl-long.73
- Volume:
- Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julian’s, Malta
- Editors:
- Yvette Graham, Matthew Purver
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1209–1222
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.eacl-long.73/
- DOI:
- Cite (ACL):
- Agnes Luhtaru, Elizaveta Korotkova, and Mark Fishel. 2024. No Error Left Behind: Multilingual Grammatical Error Correction with Pre-trained Translation Models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1209–1222, St. Julian’s, Malta. Association for Computational Linguistics.
- Cite (Informal):
- No Error Left Behind: Multilingual Grammatical Error Correction with Pre-trained Translation Models (Luhtaru et al., EACL 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.eacl-long.73.pdf