>ČASOPIS PRO MODERNÍ FILOLOGII 2026 (108) 1
Machine Translation Post-Editing — Its Principles and Specifics
ABSTRACT (en)
TThis contribution covers a relatively recent approach to non-literary translation, i.e. so-called ma chine translation post-editing (MTPE). This term means editing machine-generated translation in order to fulfil specified quality criteria. The article is divided into four sections. Following the intro duction, the second section deals with translation tools and technologies as well as with the kind of workflow that is typical of non-literary translation. It begins by defining computer-aided transla tion (CAT) tools, goes on to outline the development and types of machine translation (MT) and in troduces the functions made available by so-called generative artificial intelligence (genAI). Further topics involve aspects determining MT quality.
The third section deals specifically with MTPE and, after distinguishing its types, makes a dis tinction between MTPE and translation and/or revision while highlighting the importance of ethics when it comes to the use of MT engines.
The final section investigates the impact modern translation technologies could have on target languages, applying the concept of translation universals. Overall, the article attempts to elaborate on the benefits of the said technologies, but also on their drawbacks, and even the risks involved. The final section outlines potential future developments in the field.
KEYWORDS (en)
translation studies, human translation, machine translation, machine translation post-editing (MTPE), future developments
KLÍČOVÁ SLOVA (cz)
translatologie, překlad vyhotovený člověkem, strojový překlad, posteditace strojového překladu (MTPE), budoucí vývoj
DOI
https://doi.org/10.14712/23366591.2026.1.5
LITERATURE
Dela Cruz, J. (2024): „Amazon Researchers Find ‘Shocking Amount’ of Faulty Machine Translations in the Web“. Tech Times. Dostupné z: https://www.techtimes.com/articles/300889/20240123/amazon-researchers-find-shocking-amount-faulty-machine-translations-web.htm.
Hendy, A. — Abdelrehim, M. — Sharaf, A. — Raunak, V. — Gabr, M. — Matsushita, H. — Kim, Y. J. — Afify, M. — Awadalla, H. (2023): „How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation“. arXiv. Dostupné z doi: 10.48550/arXiv.2302.09210.
Hutchins, W. J. — Somers, H. L. (1992): An Introduction to Machine Translation. London — New York: Academic Press.
Chlumská, L. (2017): Překladová čeština a její charakteristiky. Praha: Nakladatelství Lidové noviny.
International Organization for Standardization, ISO 18587 (2017): Translation Services — Post-editing of Machine Translation Output — Requirements. Dostupné z: http://www.iso.org/iso/catalogue_detail.htm?csnumber=59149.
Kenny, D. (ed.) (2022): Machine Translation for Everyone: Empowering Users in the Age of Artificial Intelligence. Berlin: Language Science Press.
Kloudová, V. (2022): „What Could (or Maybe Should) MT Researchers Know about Translation (Theory)?“ Prezentace. Dostupné z: https://ufal.mff.cuni.cz/mtm22/files/08-what-mt-researchers-should-know-about-translation-vera-kloudova.pdf.
Kocmi, T. — Macháček, D. — Bojar, O. (2021): „The Reality of Multi-lingual Machine Translation“. In: Studies in Computational and Theoretical Linguistics. Prague: Institute of Formal and Applied Linguistics.
Koehn, P. — Knowles, R. (2017): „Six Challenges for Neural Machine Translation“. In: Proceedings of the First Workshop on Neural Machine Translation. Vancouver: Association for Computational Linguistics, s. 28–39.
Koehn, P. (2020): Neural Machine Translation. Cambridge: Cambridge University Press.
Kopecká, K. (2021): Kategorizace úprav strojového překladu při posteditaci: jazyková kombinace angličtina–čeština. Diplomová práce. Praha: Univerzita Karlova. Dostupné z: https://dspace.cuni.cz/handle/20.500.11956/148149.
Levý, J. (1983): Umění překladu. Praha: Panorama.
Petráš, P. — Munková, D. (2023): „Strojový preklad založený na neurónových sieťach — sľubná cesta prekladu z analytických jazykov do flektívnej slovenčiny?“ Slovenská reč, 88, 1, s. 74–88.
Poibeau, T. (2017): Machine Translation. Cambridge, MA & London: The MIT Press.
Rothwell, A. (ed.) (2023): Translation Tools and Technologies. London: Routledge.
Schwartz, L. (2018): „The History and Promise of Machine Translation“. In: I. Lacruz — R. Jääskeläinen (eds.), Innovation and Expansion in Translation Process Research. Amsterdam: John Benjamins Publishing Company, s. 161–190.
Svoboda, T. (2018): „The State of the (Trade and) Art in Translation: PEMT Automation, MT, and the Future“. In: European Union, European Parliament, Translation Services in the Digital World. A Sneak Peek into the (Near) Future. Luxembourg: DGT EP, s. 106–119.
Svoboda, T. (2024): „Technologie v překladu a tlumočení se zaměřením na tzv. generativní umělou inteligenci“. In: Právní překlad a role překladatele. Roma: GSE Edizioni, s. 49–62.
Svoboda, T. — Schwarz, Š. (2024): „Od přístupu bez omezení po tužku a papír: posteditace strojového překladu v překladatelsky zaměřeném studiu“. AUC Philologica, 2, s. 83–107.
Šorak, V. (2025a): „Terminologieerzwingung mit generativen LLMs. ChatGPT und Google Gemini als Übersetzungstools“. edition. Fachzeitschrift für Terminologie, 2025, 2, s. 19–24.
Šorak, V. (2025b): „Neural Machine Translation in Pandemic-Related Health Communication: A Case Study on Risks and Potentials in the Context of the Covid-19 Pandemic“. In: V. Atayan — D. Choffat — W. Czachur — E. Felder — D. Pasques (eds.), Diskursanalytische Perspektiven auf medizinische Fachkommunikation im europäischen Kontext. Heidelberg: Universitätsverlag Winter GmbH, s. 271–300. Dostupné z: https://www.winter-verlag.de/de/detail/978-3-8253-8659-7.
Toral, A. (2019): „Post-editese: An Exacerbated Translationese“. In: Proceedings of Machine Translation Summit XVII, s. 273–281.
Weatherbed, J. (2026): „OpenAI’s ChatGPT Translator Challenges Google Translate“. Dostupné z: https://www.theverge.com/news/862448/openai-chatgpt-translate-tool-launch-website.
Zouhar, V. (ed.) (2021): „Neural Machine Translation Quality and Post-editing Performance“. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, s. 10204–10214. Dostupné z: https://doi.org/10.18653/v1/2021.emnlp-main.801.
