Formulaicity of German Controlled Language as a Translation Challenge for Neural Machine Translation
https://doi.org/10.24224/2227-1295-2025-14-8-101-120
Abstract
This paper examines the formulaicity of the German, considering both its perceived and actual challenges for neural machine translation (NMT) into Russian. The study aims to conceptualize German as a controlled language for formulaic structures within the DeepL neural translator, investigating its criteria, restrictions, and output evaluation. The analysis is based on a corpus of 120 examples of German formulaic constructions, comprising two categories: verb-nominal phrases and binomial expressions. The data were sourced from the Digital Dictionary of the German Language (DWDS). We present a novel two-stage experimental design for analyzing translation choices applied to a random sample of these formulas. The methodological approach involves observing lexical-level rules for German as a controlled language. The analysis of lexical restrictions in German controlled natural language for formulaic constructions is combined with a contextual method for translation quality assessment. Our findings reveal a distinct strategy employed by the state-of-the-art DeepL translator for rendering stable formulaic expressions of varying structures. It is established that the neural approach to machine translation aims to replicate cognitive models of human thinking; however, the utilization of established translation solutions is identified here as an asset. The author emphasizes that this study does not seek to evaluate the commercial product DeepL itself, as it is a proprietary tool developed by a German corporation and tailored for texts with a specific stylistic profile.
About the Author
K. V. Manerova
St. Petersburg State University
Russian Federation
Russian Federation
Kristina V. Manerova, PhD in Philology, Associate Professor of the Department of German Philology
St. Petersburg
References
1. Babich, M. Y. (2021). Artificial intelligence and the creation of complex organizational and technical systems. News of higher educational institutions. The Volga region. Technical sciences, 4 (60): 34—42. DOI: 10.21685/2072-3059-2021-4-3. (In Russ.).
2. Burger, H. (1982). Handbuch der Phraseologie. Berlin, New York: de Gruyter. 20—56. (In Germ.).
3. Dobrovol’skij, D., Piirainen, E. (2022). Figurative Language. Cross-Cultural and Cross-Linguistic Perspectives. In: 2nd edition, revised and updated. Berlin, Boston: Walter de Gruyter GmbH. 504 р.
4. Drewer, P., Ziegler, W. (2014). Technische Dokumentation: Übersetzungsgerechte Texterstellung und Content-Management. Würzburg: Vogel. 527 S. (In Germ.).
5. Göpferich, S. (2007). Standardisierung von Kommunikation. Tübingen; Basel: A. Francke Verlag. 479—502. (In Germ.).
6. Göpferich, S. (2008). Textproduktion im Zeitalter der Globalisierung: Entwicklung einer Didaktik des Wissenstransfers. 3. Aufl. In: Studien zur Translation, 15. Tübingen: Stauffenburg Verlag. XII + 499 S. (In Germ.).
7. Häusermann, J. (1977). Phraseologie. Hauptprobleme der deutschen Phraseologie auf der Basis sowjetischer Forschungsergebnisse. In: 1. Aufl. Max Niemeyer Verlag. Tübingen: Phraseologie. 130 p. (In Germ.).
8. Heine, A. (2017). Zwischen Grammatik und Lexikon: Ein forschungsgeschichtlicher Blick auf Funktionsverbgefüge. In: In International Conference: Light Verb Constructions in Germanic Languages. Brussels: Université Saint-Louis. 452 p. (In Germ.).
9. Huijsen, W.-O. (1998). Controlled language: An introduction. In: Proceedings of the second international workshop on controlled language application (CLAW 98). Pittsburg, PA: Language Technologies Institute, Carnegie Mellon University. 1—15.
10. Kamprath, K., Adolphson, E., Mitamura, T., Nyberg, E. (1998). Controlled Language for Multilingual Document Production: Experience with Caterpillar Technical English. Carnegie Mellon University. P. 12.
11. Khabarov, V. I., Stepanov, I. S., Serenko, A. A. (2019). Controlled natural language for working with ontologies. Scientific Bulletin of Novosibirsk State Technical University, 4 (77): 99—120. DOI: 10.17212/1814-1196-2019-4-99-120. (In Russ.).
12. Kuhn, T. (2014). A Survey and Classification of Controlled Natural Languages. Computational Linguistics, 40 (1): 121—170.
13. Lehrndorfer, A. (1996). Kontrolliertes Deutsch: Linguistische und sprachpsychologische Leitlinien für eine (maschinell) kontrollierte Sprache in der Technischen Dokumentation. Tübingen: Gunter Narr. 246 S. (In Germ.).
14. Lehrndorfer, A., Reuther, U. (2008). Kontrollierte Sprache: standardisierte Sprache? Lübeck: Schmidt-Römhild (tekom Hochschulschriften). 9—121. (In Germ.).
15. Lehrndorfer, A., Schachtl, S. (1998). Controlled Siemens documentary German and TopTrans. Technical Communicators, TC-Forum (3). 8—10.
16. Manerova, K. V. (2022). Variation of Pronunciation Norm and Meaning in Light of SemanticCognitive Analysis: german Idiom das A und O. Nauchnyi dialog, 11 (7): 74—98. https://doi.org/10.24224/2227-1295-2022-11-7-74-98. (In Russ.).
17. Marzouk, Sh. (2022). Sprachkontrolle im Spiegel der Maschinellen Übersetzung: Untersuchung zur Wechselwirkung ausgewählter Regeln der Kontrollierten Sprache mit verschiedenen Ansätzen der Maschinellen Übersetzung (Translation and Multilingual Natural Language Processing 20). Berlin: Language Science Press. 698 S. (In Germ.).
18. Matusov, E. (2019). The challenges of using neural machine translation for literature. In: Proceedings of the qualities of literary machine translation. Dublin: European Association for Machine Translation. 10—19.
19. Obraztsova, V. M. (2022). The use of controlled language to improve the quality of machine translation. Problems of language and translation in the works of young scientists, 21: 140—146. (In Russ.).
20. Piotrovsky, D. D. (2020). The formula technique of Faroese ballads. Bulletin of St. Petersburg University. Language and literature, 17 (2): 271—289. DOI: org/10.21638/ spbu09.2020.207. (In Russ.).
21. Shiryaeva, A. A., Leonova, D. Y. (2024). Prospects of using machine translation based on neural networks in the translation of official business style texts. In: Philosophy and science in the cultures of the West and East. Collection of articles based on the materials of the VII All-Russian Scientific Conference with international participation. Tomsk: [b. i.]. 146—150. (In Russ.).
22. Stein, St. (1994). Neuere Literatur zur Phraseologie und zu ritualisierter Sprache. Deutsche Sprache 22. 152—180. (In Germ.).
23. Stein, St. (1995). Formelhafte Sprache. Untersuchungen zu ihren pragmatischen und kognitiven Funktionen im gegenwärtigen Deutsch (Sprache in der Gesellschaft, 22). Frankfurt am Main: Peter Lang Verlag. 375 p. (In Germ.).
24. Stein, St. (2004). Formelhaftigkeit und Routinen in mündlicher Kommunikation. Available at: https://www.degruyterbrill.com/document/doi/10.1515/9783110622768-013/html?srsltid=AfmBOooG1KBpaDDILshoX-8rGiY4078JdjFTb-U9Nequ0gAkIMI0kpI5 doi.org/10.1515/9783110622768-013 (accessed 20.03.2025). (In Germ.).
25. Stumpf, S. (2016). Formelhafte (Ir-)Regularitäten. Korpuslinguistische Befunde und sprachtheoretische Überlegungen. In: Reihe: Sprache — System und Tätigkeit, 67. Frankfurt am Main: Peter Lang Verlag. 543 S. (In Germ.).
26. Tuzovsky, A. F., Chirikov, S. V., Yampolsky, V. Z. (2005). Knowledge management systems (methods and technologies). Tomsk: NTL Publishing House. 258 p. ISBN 5-89503241-9. (In Russ.).
Review
For citations:
Manerova K.V. Formulaicity of German Controlled Language as a Translation Challenge for Neural Machine Translation. Nauchnyi dialog. 2025;14(8):101-120. (In Russ.) https://doi.org/10.24224/2227-1295-2025-14-8-101-120
Views:
88
Email this article 