Grammatical Error Correction via Sequence Tagging for Russian

Regina Nasyrova, Alexey Sorokin


Abstract
We introduce a modified sequence tagging architecture, proposed in (Omelianchuk et al., 2020), for the Grammatical Error Correction of the Russian language. We propose language-specific operation set and preprocessing algorithm as well as a classification scheme which makes distinct predictions for insertions and other operations. The best versions of our models outperform previous approaches and set new SOTA on the two Russian GEC benchmarks – RU-Lang8 and GERA, while achieve competitive performance on RULEC-GEC.
Anthology ID:
2025.acl-srw.82
Volume:
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Jin Zhao, Mingyang Wang, Zhu Liu
Venues:
ACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1036–1050
Language:
URL:
https://preview.aclanthology.org/landing_page/2025.acl-srw.82/
DOI:
Bibkey:
Cite (ACL):
Regina Nasyrova and Alexey Sorokin. 2025. Grammatical Error Correction via Sequence Tagging for Russian. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 1036–1050, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Grammatical Error Correction via Sequence Tagging for Russian (Nasyrova & Sorokin, ACL 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2025.acl-srw.82.pdf