From Rule-based Proofreader Beta Opravidlo to AI-powered Opravidlo 2.0

Žižková, Hana; Nevěřilová, Zuzana; Machura, Jakub; Horák, Aleš; Hlaváčková, Dana; Stano, Patrik

doi:10.2478/jazcas-2025-0026

Abstract

The demand for accurate and error-free written communication in Czech has led to the development of automated proofreading tools. Beta Opravidlo, a rule-based online proofreader launched in 2022, demonstrated high precision and recall in correcting Czech texts. However, its reliance on predefined linguistic rules limited recall and processing speed. With advancements in machine learning and large language models (LLMs), a transition toward AI-powered proofreading became necessary. This article explores the evolution from Beta Opravidlo to Opravidlo 2.0, integrating deep neural networks to enhance correction capabilities. We discuss proofreading as a machine learning task, compare traditional rule-based and neural approaches, and challenges such as explainability, system integration or computational requirements. The most effective solution is a hybrid approach combining rule-based precision with AI-driven adaptability. Opravidlo 2.0 aims to improve recall, optimize inference time, and extend support to other Slavic languages. This interdisciplinary effort highlights the potential of AI-powered proofreading to set new standards in language correction and usability.

References

Bojar, O. et al. (2014). Findings of the 2014 Workshop on Statistical Machine Translation. In Proceedings of the Ninth Workshop on Statistical Machine Translation, Baltimore, Maryland, USA. ACL, pp. 12–58.
Search in Google Scholar Back to article
Bryant, Ch. et al. (2023). GEC: A Survey of the State of the Art. Computational Linguistics 2023; 49(3), pp. 643–701. Accessible at: https://doi.org/10.1162/coli_a_00478.
Search in Google Scholar Back to article
Internet Language Reference Book (2025). Praha: ÚJČ AV ČR.
Search in Google Scholar Back to article
Hlaváčková D. et al. (2022). Opravidlo.
Search in Google Scholar Back to article
Kholodna, N., and Vysotska, V. (2023). Technology for grammatical errors correction in Ukrainian text content based on machine learning methods. Radio Electronics, Computer Science, Control, (1), 114. Accessible at: https://doi.org/10.15588/1607-3274-2023-1-12.
Search in Google Scholar Back to article
Kovář, V. et al. (2011). Syntactic Analysis Using Finite Patterns: A New Parsing System for Czech. In Human Language Technology. Challenges for Computer Science and Linguistics. Berlin/Heidelberg: Springer, pp. 161–171. Accessible at: http://dx.doi.org/10.1007/978-3-642-20095-3_15.
Search in Google Scholar Back to article
Křen, M. et al. (2020). SYN2020: A representative corpus of written Czech. UCNK FF UK. Accessible at: http://www.korpus.cz.
Search in Google Scholar Back to article
Liu, R. et al. (2024). Proofread: Fixes All Errors with One Tap. Accessible at: arXiv preprint arXiv:2406.04523.
Search in Google Scholar Back to article
Machura, J. et al. (2022). Automatic Grammar Correction of Commas in Czech Written Texts. Online. In: P. Sojka et al. (eds): TSD 2022. Cham (CH): Springer, pp. 113–124. Accessible at: https://dx.doi.org/10.1007/978-3-031-16270-1_10.
Search in Google Scholar Back to article
Machura, J. et al. (2023). Is it Possible to Re-educate RoBERTa? Jazykovedný časopis, 74(1), pp. 357–368. Accessible at: https://dx.doi.org/10.2478/jazcas-2023-0052.
Search in Google Scholar Back to article
Medková, H., and A. Horák. (2022). Distinguishing the Types of Coordinated Verbs with a Shared Argument by means of New ZeugBERT Language Model and ZeugmaDataset. In: A. Dimou et al. (eds.): Towards a Knowledge-Aware AI: SEMANTiCS 2022. Amsterdam: IOS Press, pp. 206–218. Accessible at: https://dx.doi.org/10.3233/SSW220022.
Search in Google Scholar Back to article
Mrkývka, V. (2023). Webový korektor jako prostředek formalizace pravidel českého jazyka. PhD Thesis, Brno: MU.
Search in Google Scholar Back to article
Omelianchuk, K. et al. (2020). GECToR – Grammatical Error Correction: Tag, Not Rewrite. In Proceedings of the 15^th Workshop on Innovative Use of NLP for Building Educational Applications, Seattle, WA, USA, pp. 163–170.
Search in Google Scholar Back to article
Prokofyev, R. et al. (2014). Correct Me If I’m Wrong: Fixing Grammatical Errors by Preposition Ranking. In Proceedings of CIKM’14. Association for Computing Machinery, New York, NY, USA, pp. 331–340. Accessible at: https://doi.org/10.1145/2661829.2661942.
Search in Google Scholar Back to article
Song, Y. et al. (2024). GEE! Grammar Error Explanation with Large Language Models. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico. ACL, pp. 754–781.
Search in Google Scholar Back to article
Straka, M. et al. (2021). RobeCzech: Czech RoBERTa, a Monolingual Contextualized Language Representation Model. In: K. Ekštein et al. (eds): TSD 2021. Lecture Notes in Computer Science, Vol. 12848. Springer, Cham. Accessible at: https://doi.org/10.1007/978-3-030-83527-9_17.
Search in Google Scholar Back to article
Wang, Y. et al. (2020). A comprehensive survey of grammar error correction. Accessible at: arXiv preprint arXiv:2005.06600.
Search in Google Scholar Back to article

From Rule-based Proofreader Beta Opravidlo to AI-powered Opravidlo 2.0

Abstract

Paradigm

My account