Neuronale maschinelle und KI-generierte Übersetzungen: Versuch einer Kategorisierung von Stärken und Schwächen in der Sprachkombination Spanisch-Deutsch
-
and
Abstract
Neural machine translation has fundamentally changed the practice of translation for more than a decade. The translation industry is now undergoing another fundamental transformation due to advances in generative artificial intelligence (GenAI) in the form of large language models (LLMs), such as ChatGPT. For professional translators, however, automatically generated translations are primarily a productivity tool. This process is known as MTPE (machine translation post-editing) and involves combining machine translations with human expertise. This article identifies and categorizes the strengths and weaknesses of automatically generated translations using a series of examples. To this end, the neural machine translation systems DeepL and Google Translate were compared with ChatGPT’s GPT-4o large language model, both with the source text and with each other. The results show that the examined automatic translations offer numerous advantages and are changing the translation profession extensively. However, they are not yet capable of ensuring an accurate translation, meaning that checking or post-editing by a human translator remains necessary.
Literaturverzeichnis
Alho, Marjut (2025): Open AI and translation quality in translations from Finnish into German: A case study. trans-kom 18(1), 273–287. https://www.trans-kom.eu/bd18nr01/trans-kom_18_01_14_Alho_AI.20250707.pdf (23.07.2025).Search in Google Scholar
Bellos, David (2011): Is that a fish in your ear? Translation and the meaning of everything. New York: Faber & Faber.Search in Google Scholar
BDÜ. (2024a): Übersetzen und Dolmetschen mit KI: Machine in the loop. https://bdue.de/aktuell/news-detail/uebersetzen-und-dolmetschen-mit-ki-machine-in-the-loop (03.08.2025).Search in Google Scholar
BDÜ. (2024b): Einsatz von Künstlicher Intelligenz im Übersetzungsprozess – Chancen, Herausforderungen und Anforderungen: Positionspapier des BDÜ. https://bdue.de/fileadmin/files/PDF/Positionspapiere/BDUe_PP_KI-Einsatz_Uebersetzen_2024.pdf (14.09.2025).Search in Google Scholar
BDÜ. (2024c): Vorsicht: Übersetzen mit ChatGPT & Co? https://bdue.de/mdue-online/vorsicht-uebersetzen-mit-chatgptco (16.08.2025).Search in Google Scholar
Centro Virtual Cervantes (2025): Refranero multilingüe. https://cvc.cervantes.es/lengua/refranero/listado.aspx (22.07.2025).Search in Google Scholar
Beaugrande, Robert A. de/Dressler, Wolfgang U. (1981): Einführung in die Textlinguistik. Tübingen: Niemeyer.10.1515/9783111349305Search in Google Scholar
Doherty, Stephen (2016): The impact of translation technologies on the process and product of translation. International Journal of Communication 10, 947–969. https://ijoc.org/index.php/ijoc/article/viewFile/3499/1573 (25.07.2025).Search in Google Scholar
Guerreiro, Nuno M./Alves, Duarte M./Waldendorf, Jonas/Haddow, Barry/Birch, Alexandra/Colombo, Pierre/Martins, André F. T. (2023): Hallucinations in large multilingual translation models. Transactions of the Association for Computational Linguistics 11. Cambridge: MIT Press, 1500–1517. https://aclanthology.org/2023.tacl-1.85/ (03.08.2025).10.1162/tacl_a_00615Search in Google Scholar
He, Sui (2024): Prompting ChatGPT for translation: A comparative analysis of translation brief and persona prompts. arXiv. https://doi.org/10.48550/arXiv.2403.00127. Search in Google Scholar
Hendy, Amr/Abdelrehim, Mohamed/Sharaf, Amr/Raunak, Vikas/Gabr, Mohamed/Matsushita, Hitokazu/Kim, Young Jin/Afify, Mohamed/Hassan, Hany (2023): How good are GPT models at machine translation? A comprehensive evaluation. arXiv. https://doi.org/10.48550/arXiv.2302.09210.Search in Google Scholar
Jiao, Wenxiang/Wang, Wenxuan/Huang, Jen-tse/Wang, Xing/Shi, Shuming/Tu, Zhaopeng (2023): Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv. https://doi.org/10.48550/arXiv.2301.08745.Search in Google Scholar
Kuklová, Michaela (2025): Der Einsatz von KI (LLM) im projektorientierten TILLT-Unterricht: Eine Fallstudie. trans-kom 18(1), 185–202. https://www.trans-kom.eu/bd18nr01/trans-kom_18_01_10_Kuklova_KI.20250707.pdf (31.01.2026).Search in Google Scholar
Meinhold, Annabelle (2023): Übersetzer im Vergleich. Google Translate vs. DeepL. https://www.cio.de/a/google-translate-vs-deepl,3575364 (13.09.2025).Search in Google Scholar
Oneword GmbH (2024): KI-Übersetzung, MTPE und LLM im Fokus: Ein Überblick. https://www.oneword.de/ki-uebersetzung-mtpe-und-llm-im-fokus/ (25.07.2025).Search in Google Scholar
Sánchez-Gijón, Pilar/Palenzuela-Badiola, Leire (2023): Analysis and evaluation of ChatGPT-induced HCI shifts in the digitalised translation process. In: Orăsan, Constantin/Mitkov, Ruslan/Corpas Pastor, Gloria/Monti, Johanna (Hg.): Proceedings of the international workshop on human-in-the-loop translation (HiT-IT 2023). Nápoles: Incoma, 157–170. https://acl-bg.org/proceedings/2023/HiT-IT%202023/pdf/2023.hitit2023-1.21.pdf (03.08.2025).Search in Google Scholar
Saunders, Danielle/Sallis, Rosie/Byrne, Bill (2020): Neural machine translation doesn’t translate gender coreference right unless you make it. arXiv. https://doi.org/10.48550/arXiv.2010.05332.Search in Google Scholar
Savoldi, Beatrice/Gaido, Marco/Bentivogli, Luisa/Negri, Matteo/Turchi, Marco (2021): Gender bias in machine translation. Transactions of the Association for Computational Linguistics 9, 845–874. https://doi.org/10.1162/tacl_a_00401.10.1162/tacl_a_00401Search in Google Scholar
Siegel, Melanie (2023): B 14 Maschinelle Übersetzung. In: Kuhlen, Rainer/Lewandowski, Dirk/Semar, Wolfgang/Womser‑Hacker, Christina (Hg.): Grundlagen der Informationswissenschaft. Berlin/Boston: De Gruyter Saur, 307–316. https://doi.org/10.1515/9783110769043-026.10.1515/9783110769043-026Search in Google Scholar
Son, Jungha/Kim, Boyoung (2023): Translation performance from the user’s perspective of large language models and neural machine translation systems. Information 14(10), 574. https://doi.org/10.3390/info14100574.10.3390/info14100574Search in Google Scholar
Sun, Zeyu/Zhang, Jie M./Harman, Mark/Papadakis, Mike/Zhang, Lu (2020): Automatic testing and improvement of machine translation. In: Proceedings of the ACM/IEEE 42nd international conference on software engineering. New York: Association for Computing Machinery, 974–985. https://dl.acm.org/doi/10.1145/3377811.3380420.10.1145/3377811.3380420Search in Google Scholar
Troles, Jonas-Dario/Schmid, Ute (2021): Extending challenge sets to uncover gender bias in machine translation: Impact of stereotypical verbs and adjectives. arXiv. https://doi.org/10.48550/arXiv.2107.11584.Search in Google Scholar
Xu, Weijia/Agrawal, Sweta/Briakou, Eleftheria/Martindale, Marianna J./Carpuat, Marine (2023): Understanding and detecting hallucinations in neural machine translation via model introspection. arXiv. https://doi.org/10.48550/arXiv.2301.07779.10.1162/tacl_a_00563Search in Google Scholar
Walter, Katharina (2025): Literarisches Übersetzen im KI-Zeitalter: Überlegungen zu einer nachhaltigen Markttransformation. Lebende Sprachen 70(1), 128–148. https://doi.org/10.1515/les-2025–0019.10.1515/les-2025-0019Search in Google Scholar
Weaver, Warren (1955): Translation. In: Locke, William N./Booth, Donald (Hg.): Machine translation of languages: Fourteen essays. Cambridge: Technology Press of the Massachusetts Institute of Technology, 15–23. https://aclanthology.org/1952.earlymt-1.1.pdf (23.07.2025).Search in Google Scholar
Welling, Kira (2019): DeepL App – Texte übersetzen, gut und einfach – so geht’s. Chip. https://praxistipps.chip.de/deepl-app-texte-uebersetzen-gut-und-einfach-so-gehts_115019 (13.09.2025).Search in Google Scholar
Wotjak, Gerd (2007): Loyalität / Treue im Hinblick worauf? Revista de Filología 25, 629–639. https://dialnet.unirioja.es/descarga/articulo/2528475.pdf (29.07.2025).Search in Google Scholar
Wotjak, Gerd (2008): Kognitive und kulturelle Aspekte des Übersetzens. Pandaemonium Germanicum 12, 149–190. https://doi.org/10.11606/1982‑8837.pg.2008.62276.10.11606/1982-8837.pg.2008.62276Search in Google Scholar
NMÜs und LLM
ChatGPT. https://chat.openai.com/Search in Google Scholar
DeepL. www.deepl.comSearch in Google Scholar
Google Translate. https://translate.google.com/?sl=de&tl=es&op=translate&hl=deSearch in Google Scholar
© 2026 Walter de Gruyter GmbH, Berlin/Boston
