AI IN NONLITERAL LANGUAGE TRANSLATION: TRANSLATING MACEDONIAN PROVERBS AND IDIOMS

Shalevska, Elena and Kostadinovska-Stojchevska, Bisera and Janusheva, Violeta and Janusheva, Maja and Stojanoska, Marija and Talevska, Marija (2025) AI IN NONLITERAL LANGUAGE TRANSLATION: TRANSLATING MACEDONIAN PROVERBS AND IDIOMS. International Journal of Education - TEACHER, 29. pp. 60-66. ISSN 1857- 8888

Full text not available from this repository.

Abstract

Translating proverbs and idioms poses a significant challenge for translators worldwide. Thus, it is no wonder
that AI models seem to struggle, too. These expressions often rely on cultural context, figurative meaning, and
linguistic creativity – things that AI models cannot really replicate. Recognizing this, this study examines how
three AI models—ChatGPT, Gemini, and DeepSeek—handle the translation of Macedonian proverbs and idioms
into English. The findings reveal several patterns: Explanation accuracy varies though all AI models consistently
provide a two-part translation; they all favor direct translations over idiomatic equivalents, provide uniform
translations of simpler proverbs, but show significant variability in word choice for more complex ones, and fail
to maintain stylistic elements such as rhyme, alliteration, and wordplay.

Item Type: Article
Subjects: Scientific Fields (Frascati) > Humanities > Languages and literature
Divisions: Faculty of Education
Depositing User: Prof. d-r Violeta Januseva
Date Deposited: 08 May 2025 16:22
Last Modified: 08 May 2025 16:22
URI: https://eprints.uklo.edu.mk/id/eprint/10929

Actions (login required)

View Item View Item