kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2026-23-2-205-217kaz29-2899Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEМЕТОДЫ ПОСТРЕДАКТИРОВАНИЯ МЕДИЦИНСКИХ ТЕКСТОВ НА КАЗАХСКОМ ЯЗЫКЕ И КАЧЕСТВЕННЫЙ АНАЛИЗMETHODS OF POST-EDITING MEDICAL TEXTS IN THE KAZAKH LANGUAGE AND QUALITATIVE ANALYSIShttps://orcid.org/0000-0003-1427-198XРахимоваД.RakhimovaD.

Доцент.

Алматы

Associate Professor.

Almaty

drakhimova060@gmail.comhttps://orcid.org/0000-0002-3641-8260ЖігерА.ZhigerA.

Магистр.

Алматы

MSc.

Almaty

aliya.zhunussova.zh@narxoz.kzhttps://orcid.org/0009-0008-5632-6188МалыхВ.MalykhV.

к.т.н.

Алматы, Санкт-Петербург

Cand. Tech. Sc.

Almaty, Saint Petersburg

valentin.malykh@phystech.eduhttps://orcid.org/0000-0002-9680-2758МансуроваМ.MansurovaM.

к. ф.-м. н., профессор.

Алматы

Cand. Phys.-Math. Sci., Professor.

Almaty

mansurova.madina@gmail.comhttps://orcid.org/0000-0002-8768-0349КарюкинВ. И.KaryukinV.

PhD.

Алматы

PhD.

Almaty

vladislav.karyukin@gmail.comКазахский национальный университет им. аль-ФарабиКазахстанAl-Farabi Kazakh National UniversityKazakhstanКазахский национальный университет им. аль-Фараби; Университет Нархоз; Международный университет информационных технологийКазахстанAl-Farabi Kazakh National University; Narxoz University; International University of Information TechnologiesKazakhstanМеждународный университет информационных технологий; Санкт-Петербургский государственный университет информационных технологий, механики и оптикиКазахстанInternational University of Information Technologies; Saint Petersburg State University of Information Technologies, Mechanics and OpticsKazakhstan202627062026232205217Copyright © Рахимова Д., Жігер А., Малых В., Мансурова М., Карюкин В.И., 20262026Рахимова Д., Жігер А., Малых В., Мансурова М., Карюкин В.И.Rakhimova D., Zhiger A., Malykh V., Mansurova M., Karyukin V.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/2899

В настоящее время в сфере медицины качественный и точный перевод с английского языка на казахский является одной из важных задач для обеспечения доступности и безопасности медицинской информации. В данной научной работе была исследована точность и эффективность систем машинного перевода, широко используемых на практике, таких как Google Translate и Yandex Translate, применительно к медицинским текстам. Основной целью исследования является рассмотрение способов семантически и стилистически корректного перевода медицинских терминов и сложных предложений с английского языка на казахский. В рамках исследования был сформирован специальный корпус, включающий 102,374 предложения, собранные из международных медицинских статей, клинических исследований и описаний лекарственных препаратов. Корпус был обучен на нейронной системе машинного перевода MarianNMT и переведен на казахский язык. Для легкого постредактирования результатов перевода использовалась трансформерная модель Kaz-RoBERTa, а для полного постредактирования – одна из больших языковых моделей (LLM), а именно GPT-4.1, при этом были рассмотрены ее возможности адаптации к медицинским текстам. Качество перевода оценивалось с использованием метрик BLEU, TER и METEOR. Результаты переводов, полученные после первоначального машинного перевода MarianNMT, были сравнены с результатами после обработки моделями Kaz-RoBERTa и GPT-4.1. Анализ показал, что переводы после применения модели Kaz-RoBERTa продемонстрировали улучшение на 9% по сравнению с исходным переводом MarianNMT, а после использования модели GPT-4.1 – на 23%.

At present, in the field of medicine, high-quality and accurate translation from English into Kazakh is one of the key challenges in ensuring the accessibility and safety of medical information. This scientific study investigates the accuracy and effectiveness of machine translation systems widely used in practice, such as Google Translate and Yandex Translate, when applied to medical texts. The main objective of the study is to explore methods for achieving semantically and stylistically correct translation of medical terminology and complex sentences from English into Kazakh. For this purpose, a specialized corpus consisting of 102,374 sentences was compiled from international medical articles, clinical studies, and drug descriptions. The corpus was processed using the MarianNMT neural machine translation system and translated into Kazakh. For light post-editing of the translation results, the transformer-based Kaz-RoBERTa model was employed, while full post-editing was carried out using one of the large language models (LLMs), namely GPT-4.1, whose adaptability to medical texts was also examined. Translation quality was evaluated using the BLEU, TER, and METEOR metrics. The translations obtained after the initial MarianNMT machine translation were compared with the results after post-editing using the Kaz-RoBERTa and GPT-4.1 models. The analysis showed that translations processed with the Kaz-RoBERTa model achieved an 9% improvement over the baseline MarianNMT translations, while the use of the GPT-4.1 model resulted in a 23% improvement.

нейронный машинный переводMarianNMTKaz-RoBERTaтрансформерная модельмедицинские текстыBLEUTERMETEORneural machine translationMarianNMTKaz-RoBERTatransformer modelmedical textsBLEUTERMETEORReferencesIssakova, S., Khassangaliyeva, B., Issakova, A., Taganova, A., Toxanbayeva, T., Kamarova, N., and Kuzdybaeva, A. The frame representation of medical terminological system in Kazakh and English. Forum for Linguistic Studies, 7 (5), 739–747 (2025). https://doi.org/10.30564/fls.v7i5.9233Issakova, S., Khassangaliyeva, B., Issakova, A., Taganova, A., Toxanbayeva, T., Kamarova, N., and Kuzdybaeva, A. The frame representation of medical terminological system in Kazakh and English. Forum for Linguistic Studies, 7 (5), 739–747 (2025). https://doi.org/10.30564/fls.v7i5.9233Kucherenko, O.F., Kuanysheva, A.B., and Keller Deditskaya, E.R. The corpus of borrowings and their functioning in the medical terminology of Kazakhstan (on the material of professional periodicals). Bulletin of the Karaganda University. Philology Series, 105 (1), 54–61 (2022). https://doi.org/10.31489/2022Ph1/54-61Kucherenko, O.F., Kuanysheva, A.B., and Keller Deditskaya, E.R. The corpus of borrowings and their functioning in the medical terminology of Kazakhstan (on the material of professional periodicals). Bulletin of the Karaganda University. Philology Series, 105 (1), 54–61 (2022). https://doi.org/10.31489/2022Ph1/54-61Forcada, M.L., Ginestí-Rosell, M., Nordfalk, J., O’Regan, J., Ortiz-Rojas, S., Pérez-Ortiz, J.A., Sánchez-Martínez, F., Ramírez-Sánchez, G., and Tyers, F.M. Apertium: A free/opensource platform for rulebased machine translation. Machine Translation, 25, 127–144 (2011). https://doi.org/10.1007/s10590-011-9090-0Forcada, M.L., Ginestí-Rosell, M., Nordfalk, J., O’Regan, J., Ortiz-Rojas, S., Pérez-Ortiz, J.A., Sánchez-Martínez, F., Ramírez-Sánchez, G., and Tyers, F.M. Apertium: A free/opensource platform for rulebased machine translation. Machine Translation, 25, 127–144 (2011). https://doi.org/10.1007/s10590-011-9090-0Assylbekov, Z., and Nurkas, A. Initial explorations in Kazakh to English statistical machine translation. In: Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014, pp. 12–16 (2014). Available at: https://clic2014.fileli.unipi.it/proceedings/vol1/CLICIT201413.pdfAssylbekov, Z., and Nurkas, A. Initial explorations in Kazakh to English statistical machine translation. In: Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 and of the Fourth International Workshop EVALITA 2014, pp. 12–16 (2014). Available at: https://clic2014.fileli.unipi.it/proceedings/vol1/CLICIT201413.pdfAssylbekov, Z., Myrzakhmetov, B., and Makazhanov, A. Experiments with Russian to Kazakh sentence alignment. In: Proceedings of the 4th International Conference on Computer Processing of Turkic Languages (2016). Available at: https://nur.nu.edu.kz/handle/123456789/1694Assylbekov, Z., Myrzakhmetov, B., and Makazhanov, A. Experiments with Russian to Kazakh sentence alignment. In: Proceedings of the 4th International Conference on Computer Processing of Turkic Languages (2016). Available at: https://nur.nu.edu.kz/handle/123456789/1694Vieira, L.N., Alonso, E., and Bywood, L. Introduction: Post-editing in practice—Process, product and networks. Journal of Specialized Translation, 31, 2–13 (2019). https://doi.org/10.26034/cm.jostrans.2019.173Vieira, L.N., Alonso, E., and Bywood, L. Introduction: Post-editing in practice—Process, product and networks. Journal of Specialized Translation, 31, 2–13 (2019). https://doi.org/10.26034/cm.jostrans.2019.173Shterionov, D., do Carmo, F., Moorkens, J., Hossari, M., Wagner, J., Paquin, E., Schmidtke, D., Groves, D., and Way, A. A roadmap to neural automatic post-editing: An empirical approach. Machine Translation, 34, 67–96 (2020). https://doi.org/10.1007/s10590-020-09249-7Shterionov, D., do Carmo, F., Moorkens, J., Hossari, M., Wagner, J., Paquin, E., Schmidtke, D., Groves, D., and Way, A. A roadmap to neural automatic post-editing: An empirical approach. Machine Translation, 34, 67–96 (2020). https://doi.org/10.1007/s10590-020-09249-7Rakhimova, D., and Karibayeva, A. Aligning and extending technologies of parallel corpora for the Kazakh language. Eastern European Journal of Enterprise Technologies, 4 (2(118)), 32–39 (2022). https://doi.org/10.15587/1729-4061.2022.259452Rakhimova, D., and Karibayeva, A. Aligning and extending technologies of parallel corpora for the Kazakh language. Eastern European Journal of Enterprise Technologies, 4 (2(118)), 32–39 (2022). https://doi.org/10.15587/1729-4061.2022.259452Zhumanov, Z., and Tukeyev, U. Integrated technology for creating quality parallel corpora. In: Advances in Computational Collective Intelligence (Springer, Cham, 2021), pp. 511–524. https://doi.org/10.1007/978-3030-88113-9_41Zhumanov, Z., and Tukeyev, U. Integrated technology for creating quality parallel corpora. In: Advances in Computational Collective Intelligence (Springer, Cham, 2021), pp. 511–524. https://doi.org/10.1007/978-3030-88113-9_41Karyukin, V., Rakhimova, D., Karibayeva, A., Turganbayeva, A., and Turarbek, A. The neural machine translation models for the low-resource Kazakh–English language pair. PeerJ Computer Science, 9, e1224 (2023). https://doi.org/10.7717/peerj-cs.1224Karyukin, V., Rakhimova, D., Karibayeva, A., Turganbayeva, A., and Turarbek, A. The neural machine translation models for the low-resource Kazakh–English language pair. PeerJ Computer Science, 9, e1224 (2023). https://doi.org/10.7717/peerj-cs.1224Rakhimova, D., Sagat, K., Zhakypbaeva, K., and Zhunussova, A. Development and study of a postediting model for Russian-Kazakh and English-Kazakh translation based on machine learning. In: Advances in Computational Collective Intelligence (Springer, Cham, 2021), pp. 525–534. https://doi.org/10.1007/9783-030-88113-9_42Rakhimova, D., Sagat, K., Zhakypbaeva, K., and Zhunussova, A. Development and study of a postediting model for Russian-Kazakh and English-Kazakh translation based on machine learning. In: Advances in Computational Collective Intelligence (Springer, Cham, 2021), pp. 525–534. https://doi.org/10.1007/9783-030-88113-9_42Gulcehre, C., Ahn, S., Nallapati, R., Zhou, B., and Bengio, Y. Pointing the unknown words. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 140–149 (2016). https://doi.org/10.18653/v1/P16-1014Gulcehre, C., Ahn, S., Nallapati, R., Zhou, B., and Bengio, Y. Pointing the unknown words. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 140–149 (2016). https://doi.org/10.18653/v1/P16-1014Li, X., Zhang, J., and Zong, C. Towards zero unknown word in neural machine translation. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 2852–2858 (New York, NY, USA, 2016). Available at: https://www.ijcai.org/proceedings/2016Li, X., Zhang, J., and Zong, C. Towards zero unknown word in neural machine translation. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 2852–2858 (New York, NY, USA, 2016). Available at: https://www.ijcai.org/proceedings/2016Rakhimova, D., Turarbek, A., Karyukin, V., Karibayeva, A., and Turganbayeva, A. The development of the light post-editing module for English-Kazakh translation. In: Proceedings of the 7th International Conference on Engineering & MIS (Almaty, Kazakhstan, 2021). https://doi.org/10.1145/3492547.3492651Rakhimova, D., Turarbek, A., Karyukin, V., Karibayeva, A., and Turganbayeva, A. The development of the light post-editing module for English-Kazakh translation. In: Proceedings of the 7th International Conference on Engineering & MIS (Almaty, Kazakhstan, 2021). https://doi.org/10.1145/3492547.3492651Martikainen, H. Post editing neural MT in medical LSP: Lexico grammatical patterns and distortion in the communication of specialized knowledge. Informatics, 6 (3), 26 (2019). https://doi.org/10.3390/ informatics6030026Martikainen, H. Post editing neural MT in medical LSP: Lexico grammatical patterns and distortion in the communication of specialized knowledge. Informatics, 6 (3), 26 (2019). https://doi.org/10.3390/ informatics6030026Lee, W., Park, J., Go, B.-H., and Lee, J.-H. Transformer-based automatic post-editing with a contextaware encoding approach for multi-source inputs. arXiv preprint arXiv:1908.05679 (2019).Lee, W., Park, J., Go, B.-H., and Lee, J.-H. Transformer-based automatic post-editing with a contextaware encoding approach for multi-source inputs. arXiv preprint arXiv:1908.05679 (2019).Rubino, R., Huet, S., Lefèvre, F., and Linarès, G. Statistical post editing of machine translation for domain adaptation. In: Cettolo, M., Federico, M., Specia, L., and Way, A. (Eds.), Proceedings of the 16th Annual Conference of the European Association for Machine Translation, pp. 221–228 (2012). Available at: https://aclanthology.org/2012.eamt-1.55/Rubino, R., Huet, S., Lefèvre, F., and Linarès, G. Statistical post editing of machine translation for domain adaptation. In: Cettolo, M., Federico, M., Specia, L., and Way, A. (Eds.), Proceedings of the 16th Annual Conference of the European Association for Machine Translation, pp. 221–228 (2012). Available at: https://aclanthology.org/2012.eamt-1.55/Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H., Heafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A.F., Bogoychev, N., Martins, A.F.T., and Birch, A. Marian: Fast neural machine translation in C++. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 116–121 (2018). https://doi.org/10.18653/v1/P18-4020Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H., Heafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A.F., Bogoychev, N., Martins, A.F.T., and Birch, A. Marian: Fast neural machine translation in C++. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 116–121 (2018). https://doi.org/10.18653/v1/P18-4020Baitenova, L., Tussupova, S., Mambetov, S., Munaitbas, G., and Mukhamejanova, G. Hybrid artificial intelligence architectures for automatic text correction in the Kazakh language. Frontiers in Artificial Intelligence, 8, Article 1708566 (2025). https://doi.org/10.3389/frai.2025.1708566Baitenova, L., Tussupova, S., Mambetov, S., Munaitbas, G., and Mukhamejanova, G. Hybrid artificial intelligence architectures for automatic text correction in the Kazakh language. Frontiers in Artificial Intelligence, 8, Article 1708566 (2025). https://doi.org/10.3389/frai.2025.1708566Xu, H., Kim, Y.J., Sharaf, A., and Awadalla, H.H. A paradigm shift in machine translation: Boosting translation performance of large language models. arXiv preprint arXiv:2309.11674 (2023).Xu, H., Kim, Y.J., Sharaf, A., and Awadalla, H.H. A paradigm shift in machine translation: Boosting translation performance of large language models. arXiv preprint arXiv:2309.11674 (2023).Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y.J., Afify, M., and Awadalla, H.H. How good are GPT models at machine translation? A comprehensive evaluation. arXiv preprint arXiv:2302.09210 (2023).Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y.J., Afify, M., and Awadalla, H.H. How good are GPT models at machine translation? A comprehensive evaluation. arXiv preprint arXiv:2302.09210 (2023).Jiao, W., Wang, W., Huang, J.-T., Wang, X., and Tu, Z. Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv preprint arXiv:2301.08745 (2023).Jiao, W., Wang, W., Huang, J.-T., Wang, X., and Tu, Z. Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv preprint arXiv:2301.08745 (2023).Reiter, E. A structured review of the validity of BLEU. Computational Linguistics, 44 (3), 393–401 (2018). https://doi.org/10.1162/COLI_a_00322Reiter, E. A structured review of the validity of BLEU. Computational Linguistics, 44 (3), 393–401 (2018). https://doi.org/10.1162/COLI_a_00322Lavie, A., and Agarwal, A. METEOR: An automatic metric for MT evaluation with high levels of correlation with human judgments. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 228–231 (2007). URL: https://aclanthology.org/W07-0734Lavie, A., and Agarwal, A. METEOR: An automatic metric for MT evaluation with high levels of correlation with human judgments. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 228–231 (2007). URL: https://aclanthology.org/W07-0734Snover, M., Dorr, B., Schwartz, R., Micciulla, L., and Makhoul, J. A study of translation edit rate with targeted human annotation. In: Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, pp. 223–231 (2006). URL: https://aclanthology.org/2006.amta-papers.25/Snover, M., Dorr, B., Schwartz, R., Micciulla, L., and Makhoul, J. A study of translation edit rate with targeted human annotation. In: Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, pp. 223–231 (2006). URL: https://aclanthology.org/2006.amta-papers.25/

The authors declare that there are no conflicts of interest present.