Abstract
We offer a two-stage reranking method for grammatical error correction: the first model serves as edit generator, while the second classifies the proposed edits as correct or false. We show how to use both encoder-decoder and sequence labeling models for the first step of our pipeline. We achieve state-of-the-art quality on BEA 2019 English dataset even using weak BERT-GEC edit generator. Combining our roberta-base scorer with state-of-the-art GECToR edit generator, we surpass GECToR by 2-3%. With a larger model we establish a new SOTA on BEA development and test sets. Our model also sets a new SOTA on Russian, despite using smaller models and less data than the previous approaches.- Anthology ID:
- 2022.emnlp-main.785
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11416–11429
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.785
- DOI:
- 10.18653/v1/2022.emnlp-main.785
- Cite (ACL):
- Alexey Sorokin. 2022. Improved grammatical error correction by ranking elementary edits. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11416–11429, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Improved grammatical error correction by ranking elementary edits (Sorokin, EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2022.emnlp-main.785.pdf