Basic Algorithm for Automatic Spelling Correction of Russian Texts: Development, Evaluation and Prospects

Cover Page

Cite item

Full Text

Abstract

Automatic spelling check and correction of texts in Russian is an urgent task in the field of natural language processing. Our research is aimed at developing, evaluating, and describing a computer programme for correcting spelling errors with high accuracy. The proposed method is based on line-by-line text processing using rules for spelling and capitalisation accuracy and a probabilistic model for proposing candidate words for error correction. Our algorithm operates at the level of individual words, which limits its ability to take context into account. The metrics used to test the quality of the model are Precision, Recall, and F1 Score. For ease of use and program refinement, we integrated automated error analysis and detailed report generation to identify the strengths and weaknesses of the algorithm. The detailed development description ensures the reproducibility of the algorithm and is in line with the Open-source ideology. The results showed that the algorithm has high Precision = 1.00, i.e., it corrects only those spelling errors that were specified in the reference text. However, the Recall = 0.84 emphasises the need for further refinement, including handling context-dependent errors and processing stable expressions. The F1 Score = 0.91 confirms the balanced performance of the algorithm and justifies its use as a basic model of text correction in Russian. The conclusions of the study emphasise the potential of the algorithm in the tasks of automatic correction of Russian-language text, and suggest prospective areas for improving the source code, such as the use of n-grams and language models. This work lays the foundation for further research in the field of automatic correction of Russian-language texts.

About the authors

E. V. Isaeva

Perm State University

Email: ekaterinaisae@psu.ru
Scopus Author ID: 57204498718
ResearcherId: O-6777-2015
Perm

B. Z. Safarbekov

National University of Science and Technology "MISIS"

Email: behruzsafarbekov3@gmail.com
Moscow

References

  1. Zukarnain, N., Abbas, B. S., Wayan, S., Trisetyarso, A. and Kang, C. H. (2019), "Spelling Checker Algorithm Methods for Many Languages", in: 2019 International Conference on Information Management and Technology (ICIMTech). IEEE, pp. 198-201. https://doi.org/10.1109/ICIMTech.2019.8843801.
  2. Hamrouni, B. M. (1994), "Logic compression of dictionaries for multilingual spelling checkers, in: Proceedings of the 15th Conference on Computational Linguistics", Association for Computational Linguistics, Morristown, NJ, USA, p. 292. https://doi.org/10.3115/991886.991936.
  3. Lokhande, H. A., Kinage, L. J., Kolunkar, P. M., Salunkhe, J. M. and Kale, S. (2024), "Enhancing Text Quality with Bi-LSTM: An Approach for Automated Spelling and Grammar Correction", in: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), IEEE, pp. 01-07, https://doi.org/10.1109/ADICS58448.2024.10533521.
  4. Mangu, L. and Brill, E. (1997), "Automatic Rule Acquisition for Spelling Correction", in: Proceedings of the Fourteenth International Conference on Machine Learning (ICML '97), Morgan Kaufmann Publishers Inc, San Francisco, CA, USA, pp. 187-194.
  5. Davrondjon, G. and Janowski, T. (2002), "Developing a Spell-Checker for Tajik Using RAISE", in: George, C., Miao, H. (Eds.), Formal Methods and Software Engineering, ICFEM 2002. Lecture Notes in Computer Science. Springer, Berlin, Heidelberg, pp. 401-405. https://doi.org/10.1007/3-540-36103-0_41.
  6. Atawy, S. M. El, and ElGhany, A. A. (2018), "Automatic Spelling Correction based on n-Gram Model". Int J Comput Appl 182, pp. 5-9. https://doi.org/10.5120/ijca2018917724.
  7. Chen, K.-Y., Wang, H.-M. and Chen, H.-H. (2015), "A Probabilistic Framework for Chinese Spelling Check", ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 14, no. 4, pp. 1-17. https://doi.org/10.1145/2826234.
  8. Sasu, L. (2011), "A Probabilistic Model for Spelling Correction", Bulletin of the Transilvania University of Brasov, Series III: Mathematics, Informatics, Physics, vol. 4(53), no. 2, pp. 141-146.
  9. Kashyap, R. L. and Oommen, B. J. (1984), "Spelling correction using probabilistic methods", Pattern Recognit, Lett, vol. 2, no. 3, pp. 147-154. https://doi.org/10.1016/0167-8655(84)90038-2.
  10. Chen, S. F. (1996), "Building Probabilistic Models for Natural Language".
  11. Flachs, S., Lacroix, O. and Søgaard, A. (2019), "Noisy Channel for Low Resource Grammatical Error Correction", in: Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 191-196. https://doi.org/10.18653/v1/W19-4420.
  12. Li, Y., Anastasopoulos, A. and Black, A. W. (2020), "Towards Minimal Supervision BERT-Based Grammar Error Correction (Student Abstract)", Proceedings of the AAAI Conference on Artificial Intelligence vol. 34, no. 10, pp. 13859-13860. https://doi.org/10.1609/aaai.v34i10.7202.
  13. Khabutdinov, I. A., et al. (2024), "RuGECToR: Rule-Based Neural Network Model for Russian Language Grammatical Error Correction", Programming and Computer Software. Pleiades Publishing, vol. 50, no. 4, pp. 315-321.
  14. Martynov, N. et al. (2023), "A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages".
  15. Kaggle: Your Machine Learning and Data Science Community [Electronic resource]. URL: https://www.kaggle.com/ (accessed: 07.02.2025).
  16. Hugging Face - The AI community building the future. [Electronic resource]. URL: https://huggingface.co/ (accessed: 07.02.2025).
  17. Language-tool-python.PyPI [Electronic resource]. URL: https://pypi.org/project/language-tool-python/ (accessed: 11.12.2024).
  18. Hunspell download SourceForge.net [Electronic resource]. URL: https://sourceforge.net/projects/hunspell/ (accessed: 02.02.2025).
  19. Goslin, K. and Hofmann, M. (2022), "English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics", Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022). Marseille: European Language Resources Association (ELRA), pp. 458-464.
  20. SymSpell, Github [Electronic resource]. URL: https://github.com/wolfgarbe/SymSpell (accessed: 02.02.2025).
  21. Audah, H. A., Yuliawati, A. and Alfina I. (2023) "A Comparison Between SymSpell and a Combination of Damerau-Levenshtein Distance with the Trie Data Structure, 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA). IEEE, pp. 1-6.
  22. Spelling, grammar and style checker online - LanguageTool [Electronic resource] URL: https://languagetool.org/ru (accessed: 02.02.2025).
  23. Sorokin, A. A. and Shavrina, T. (2016), "Automatic spelling correction for Russian social media texts", in: Dialogue, International Conference on Computational Linguistics, https://www.researchgate.net/publication/303813582_Automatic_spelling_correction_for_Russian_social_media_texts, Moscow.
  24. Pandas 2.2.3 documentation [Electronic resource]. URL: https://pandas.pydata.org/docs/ (accessed: 02.02.2025).

Supplementary files

Supplementary Files
Action
1. JATS XML
Download


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).