What type of study is this?

This is a Quantitative Study study.

Copilot vs DeepSeek’s Translation of Denotative and Metonymic Abu- and Umm- Animal and Plant Folk Names in Arabic

View Full Paper

Ask AI

Bookmark

Authors

This analysis shows the translation accuracy of denotative and metonymic names by AI tools, suggesting areas for improvement.

DeepSeek achieved higher accuracy in translating denotative Abu-names using both no-domain and domain prompts, outperforming Copilot.
Both AI tools struggled with metonymic names, with less than 3% accuracy across all prompts, indicating significant translation challenges.
Faulty strategies included translating Abu names directly to 'father' and treating metonymic names as personal names, highlighting their limitations.
The study provides insights into causes of errors in AI translations and offers recommendations for enhancing performance in this area.

Reima Al-Jarf (2025) studied this question.

View Full Paper

Ask AI

Bookmark