Challenges of Machine Translation for Expressions Containing Geographical Proper Names: Between Accuracy and Context
DOI:
https://doi.org/10.35516/Hum.2026.10995Keywords:
Machine translation, geographical proper names, cross-cultural communication, linguistic challenges, Machine translation of geographical expressions, cultural connotations, translation accuracy.Abstract
Objectives:This study aims to evaluate the strengths and limitations of machine translation when dealing with expressions related to geographical proper names, focusing on how the cultural significance of these names impacts translation accuracy.
Methods: A set of idiomatic expressions associated with place names was collected from various online sources and reference dictionaries such as Le Figaro Expressions, L'Internaute Expressions, Expressio, Le Robert d’expressions, and Larousse des expressions. These samples were processed through Google Translate, both in context and out of context. The translations were then critically analyzed from a translation studies perspective to identify strengths and weaknesses.
Results: The study revealed that machine translation encounters notable difficulties when translating culturally loaded expressions, especially when context is lacking. However, some encouraging results were observed when contextual information was provided, with the tool managing, in certain cases, to produce accurate translations.
Conclusions: Despite the significant progress made in machine translation, handling culturally charged expressions—particularly toponymic expressions—remains imperfect. The study recommends that machine translations be carefully reviewed by experts and supplemented with reference resources such as dictionaries and encyclopedias to ensure accuracy and reliability.
Downloads
References
Angermeyer, P., & Pym, A. (2008). La traduction comme appropriation : le cas des toponymes étrangers. Meta, 53(3), 635–653. https://www.erudit.org/fr/revues/meta/2008-v53-n3-meta1442/014333ar.pdf
Arab Academy. (2028). Digital translation: an organic turn in the process of machine translation. Arabic language complex in Damascus.
Hansen, D., Esperança-Rodier, E., Blanchon, H., & Bada, V. (2022). Adapter la machine à la traduction humaine individualisée. https://jdmdh.episciences.org/9949/pdf
Lecuit, É. (2012). Les tribulations d'un nom propre en traduction : Étude contrastive du nom propre et de sa traduction à partir d'un corpus aligné de dix langues européennes. Thèse de doctorat, Université de Lorraine. https://hal.science/tel-01113083
Lee, A. G., & Smith, D. L. (2012). A survey of machine translation techniques for multiword expressions. Computational Linguistics, 38(2), 367-401. https://doi.org/10.1162/COLI_a_00073
Liu, Y., & Liu, Q. (2019). A Survey of Named Entity Recognition and Classification. Journal of Computer Science and Technology, 34(6), 1135–1158. https://doi.org/10.1007/s11390-019-1943-6
Sharma, R., Katyayan, P., & Joshi, N. (2023). Improving the Quality of Neural Machine Translation Through Proper Translation of Name Entities. arXiv preprint arXiv:2305.07360. https://arxiv.org/abs/2305.07360
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Dirasat: Human and Social Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
