Revisiting Machine Translation Post-Editing Workflows with AI: Insights from a Case Study

Year 2025, Volume: 8 Issue: 2, 85 - 116, 31.12.2025

Işın Öner , Zehra Begüm Bengi

https://doi.org/10.29228/transLogos.82

Abstract

Recent advances in neural machine translation and generative AI have reshaped translation and technical communication workflows, raising new questions about the role and scope of post-editing. This article reports on a case study, examining how machine translation and large language models perform in translation and post-editing scenarios. A Turkish user-manual text prepared for the purposes of the study was translated into English using Google Translate and ChatGPT under zero-shot conditions with no pre-editing to reflect common industry scenarios. Both tools produced fluent and largely accurate translations; however, the resulting outputs retained many of the instructional and usability issues present in the original text, such as long sentence structures, repetition, weak imperative style, and non-linear task flow. These findings underscore the distinction between linguistic accuracy and functional usability in technical communication. The study then explores how instruction-based prompting can support AI-assisted revision aligned with user-manual standards and plain-language principles, followed by expert human refinement. This two-stage process allows for a closer examination of how responsibility for text quality is distributed between the source text, the AI system, and the human professional. The article offers empirical insight into how post-editing functions in contemporary hybrid environments and discusses implications for professional training, emphasizing the need for competencies in source-text evaluation, prompt design, standards awareness, and human–AI collaboration. The study situates generative AI within existing post-editing practices and highlights its potential as a supportive, task-oriented assistant when guided by professional judgment.

Keywords

post-editing , machine translation , generative artificial intelligence , prompting , text optimization

References

• Algaraady, Jeehaan, and Mohammad Mahyoob. 2025. “Exploring ChatGPT’s Potential for Augmenting Post-editing in Machine Translation across Multiple Domains: Challenges and Opportunities.” Frontiers in Artificial Intelligence 8:1526293. doi:10.3389/frai.2025.1526293.
• Alimen, Nilüfer. 2023. “Makine Çevirisinden Sohbet Robotu Çevirisine: ChatGPT ile Deneysel Bir Çalışma.” [From machine translation to chatbot translation: An experimental study with ChatGPT.] RumeliDE Journal of Language and Literature Studies, no. 36, 1532–1548. doi:10.29000/rumelide.1369589.
• Alimen, Nilüfer, Muhammed Baydere, Hülya Boy, Senem Bulut, Gökhan Doğru, Ayşe Banu Karadağ, and Işın Öner. 2023. “İngilizce-Türkçe Dil Çiftinde Makine Çevirisi Hata Analizi: İnsanın Merkezde Olduğu Bir Kalite Değerlendirme Araştırması.” [Machine translation error analysis in the English-Turkish language pair: A human-centered quality assessment study.] In 1. Ulusal Çeviri Teknolojileri Kongresi Bildiri Özetleri [Book of abstracts of the 1st National Congress on Translation and Interpreting Technologies], 40–41. https://ceviriteknolojileri.bogazici.edu.tr/sites/ceviriteknolojileri.boun.edu.tr/files/ctk2023_bildiri_ozetleri.pdf.
• Allen, Jeffrey. 2003. “Post-editing.” In Computers and Translation: A Translator’s Guide, edited by Harold Somers, 297– 317. Amsterdam: John Benjamins.
• ALPAC (Automatic Language Processing Advisory Committee). 1966. Language and Machines: Computers in Translation and Linguistics; A Report by the Automatic Language Processing Advisory Committee, Division of Behavioral Sciences, National Academy of Sciences, National Research Council.
• Bar-Hillel, Yehoshua. 1951. “The Present State of Research on Mechanical Translation.” American Documentation 2 (4): 229–237. doi:10.1002/asi.5090020408.
• Baydere, Muhammed, and Aziz Berkan Karadeli. 2023. “Machine Translation Quality in English–Turkish and Turkish–English Culinary Texts on Social Media: A Human Annotation Study.” Paper presented at the 9th International KTUDELL Conference on Language, Literature, and Translation, Trabzon, September 25–26.
• Doğan, Mehmet Ferit. 2025. “From Prompts to Precision: A Comparative Experimental Study of Translation Quality Outputs with Focus on Role-Based (Persona) Prompting for Medical Texts.” Unpublished master’s thesis, Istanbul 29 Mayıs University.
• Doğru, Gökhan, and Joss Moorkens. 2024. “Data Augmentation with Translation Memories for Desktop Machine Translation Fine-tuning in 3 Language Pairs.” The Journal of Specialised Translation, no. 41, 149–178. doi:10.26034/cm.jostrans.2024.4716.
• ELIS. 2025. European Language Industry Survey 2025: Trends, Expectations and Concerns of the European Language Industry.
• IEC/IEEE. 2019. IEC/IEEE 82079-1:2019 Preparation of Information for Use (Instructions for Use) of Products – Part 1: Principles and General Requirements.
• ISO. 2017. ISO 18587:2017 Translation Services — Post-editing of Machine Translation Output — Requirements.
• Kuhn, Thomas S. 1962. The Structure of Scientific Revolutions. Chicago: University of Chicago Press.
• Lem, Stanisław. (1974) 2014. The Cyberiad. Translated by Michael Kandel. Great Britain: Penguin Classics.
• Massardo, Isabella, Jaap van der Meer, Sharon O’Brien, Fred Hollowood, Nora Aranberri, and Katrin Drescher. 2016. MT Post-Editing Guidelines. Amsterdam: TAUS Signature Editions.
• Moorkens, Joss, Andy Way, and Séamus Lankford. 2025. Automating Translation. Oxford: Routledge.
• Nimdzi. 2025. The 2025 Nimdzi 100. https://www.nimdzi.com/nimdzi-100-2025/.
• OECD. 2023. OECD Employment Outlook 2023: Artificial Intelligence and the Labour Market. Paris: OECD Publishing. doi:10.1787/08785bba-en.
• Öner Bulut, Senem. 2019. “Integrating Machine Translation into Translator Training: Towards ‘Human Translator Competence’?” transLogos Translation Studies Journal 2 (2): 1–26. doi:10.29228/transLogos.11.
• Öner Bulut, Senem, and Nilüfer Alimen. 2023. “Translator Education as a Collaborative Quest for Insights into the Re-positioning of the Human Translator (Educator) in the Age of Machine Translation: The Results of a Learning Experiment.” In “(Re-)profiling T&I Education: Meeting Evolution with Innovation,” edited by Gary Massey, Maria Piotrowska, and Mariusz Marczak. Special Issue, The Interpreter and Translator Trainer 17 (3): 375–392. doi:10.1080/1750399x.2023.2237837.
• Öner, Işın, and Senem Öner Bulut. 2021. “Post-Editing Oriented Human Quality Evaluation of Neural Machine Translation in Translator Training: A Study on Perceived Difficulties and Benefits.” transLogos Translation Studies Journal 4 (1): 100–124. doi:10.29228/transLogos.33.
• Öner, Işın, and Zehra Begüm Bengi. 2024. “Essential or Obsolete? The Role of Human Competencies in the Tech-Driven Language Services Industry.” transLogos Translation Studies Journal 7 (1): 78–104. doi:10.29228/transLogos.66.
• Öner, Işın, and Zehra Begüm Bengi. 2025. “Prompt, Evaluate, Revise: AI-Assisted User Manual Creation in Academic Practice.” transLogos Translation Studies Journal 8 (1): 103–347. doi:10.29228/transLogos.78.
• Öztürk Baydere, Hilal. 2022. “Makine Çevirisi ve Dijitalleşme Bağlamında Çevirmenlik Mesleğinin Dönüşümü.” [Transformation of the translation profession within the context of machine translation and digitalization.] Unpublished PhD diss., Istanbul University.
• Öztürk Baydere, Hilal. 2023. “Rethinking Translator Competence in the Machine Translation Era.” transLogos Translation Studies Journal 6 (1): 45–74. doi:10.29228/transLogos.54.
• Poibeau, Thierry. 2017. Machine Translation. Massachusetts: The MIT Press.
• Raunak, Vikas, Amr Sharaf, Yiren Wang, Hany Hassan Awadalla, and Arul Menezes. 2023. “Leveraging GPT-4 for Automatic Translation Post-Editing.” In Findings of the Association for Computational Linguistics: EMNLP 2023, 12009–12024. Singapore: Association for Computational Linguistics.
• Reifler, Erwin. 1952. “Mechanical Translation with a Pre-Editor and Writing for Mechanical Translation.” Paper presented at the Conference on Mechanical Translation, M.I.T. (Massachusetts Institute of Technology), Cambridge, Massachusetts, June 17–20.
• Sayın, Ayşe Betül. 2025. “Learning to Learn: Translators’ Post-Editing Patterns and Priming.” Unpublished PhD diss., Istanbul 29 Mayıs University.
• TAUS. 2010. Machine Translation Postediting Guidelines.
• Wang, Haifeng, Hua Wu, Zhongjun He, Liang Huang, and Kenneth Ward Church. 2022. “Progress in Machine Translation.” Engineering 18:143–153. doi:10.1016/j.eng.2021.03.023.
• Zhang, Jia, and Stephen Doherty. 2025. “Investigating Novice Translation Students’ AI Literacy in Translation Education.” In “Transforming Translation Education through Artificial Intelligence,” edited by Feng Cui, Defeng Li, and Chiyuan Zhuang. Special Issue, The Interpreter and Translator Trainer 19 (3–4): 234–253. doi:10.1080/1750399X.2025.2541478.