Translation of Arabic Folk Medical Terms with Om and Abu by AI: A Comparison of Microsoft Copilot and DeepSeek

Although "أم om" and " أبو abu" in Arabic literally mean "mother" and "father", they have several meanings, usages, and are used in numerous contexts. They are used in some surnames, technical expressions, metonyms, general collocations, and idioms. They are used in names of people, cities, monuments, birds, insects, fish, animals, plants, brands, names of medicines (أبو نمر Tiger balm), body organs (أم التلافيف many plies), and disease names and medical conditions (أبو دغيم mumps) where they are used as a prefix and do not mean “mother”. Due to their extensive use in folk medical terms, this study investigates the translation of Arabic folk medical terms containing Om and Abu by Microsoft Copilot (MC) and DeepSeek (DS) in terms of accuracy, the translation strategies they use, the causes of translation errors and whether translation students can depend on AI in translating such terms. Analysis of a sample of 205 Arabic folk medical terms containing Om- and Abu by MC and DS showed that 46% of the terms were correctly translated by MC and 66% by DS (أُمُّ الدَّمِ الأَوَّلِيَّة primary aneurysm,أُمُّ الدَّمِ البَطْنِيَّة abdominal aneurysm). MC rendered more literal word-for word translations than DS (16% and 11% respectively). Here أم Om and أبو Abu were literally translated as “mother” and “father” not as a prefix. أبو الرّكَب was translated as “father of the knees” instead of “dengue”, أم التلافيف “mother of folds” instead of omasum psalterium. MC and DS rendered lexical variants (synonyms) as cerebral aneurysm for أُمُّ الدَّمِ الدِّماغِيَّة instead of brain aneurysm. Both MC and DS rendered equivalents with a different word order from the dictionary definition (cavernous carotid aneurysm for أُمُّ الدَّمِ السُّباتِيَّةُ الكَهْفِيَّة instead of caroticocavernous aneurysm). AI translated folk medical terms containing أم Om & أبو Abu with lower accuracy than modern medical terms but higher accuracy rate than expressions of impossibility, Gaza-Israel war terminology, grammatical terms used metaphorically, and zero expressions which are current and commonly used by Arabic speakers. Comparisons with human translation of Om and Abu expressions, strategies used, causes of mistranslations and why DS outperformed MC in translating were made. Users need to understand how to prompt and guide AI models by specifying the context, intent, and audience and should interpret AI outputs critically.

Authors

Publication Details

Journal
Journal of Medical and Health Studies
Published
2025-09-20
DOI
https://doi.org/10.32996/jmhs.2025.6.4.8
Primary Topic
Natural Language Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Translation of Arabic Folk Medical Terms with Om and Abu by AI: A Comparison of Microsoft Copilot and DeepSeek

Reima Al-Jarf
Journal of Medical and Health Studies
Natural Language Processing Techniques
article

Translation of Arabic Folk Medical Terms with Om and Abu by AI: A Comparison of Microsoft Copilot and DeepSeek

Reima Al-Jarf
article en

Abstract

Although "أم om" and " أبو abu" in Arabic literally mean "mother" and "father", they have several meanings, usages, and are used in numerous contexts. They are used in some surnames, technical expressions, metonyms, general collocations, and idioms. They are used in names of people, cities, monuments, birds, insects, fish, animals, plants, brands, names of medicines (أبو نمر Tiger balm), body organs (أم التلافيف many plies), and disease names and medical conditions (أبو دغيم mumps) where they are used as a prefix and do not mean “mother”. Due to their extensive use in folk medical terms, this study investigates the translation of Arabic folk medical terms containing Om and Abu by Microsoft Copilot (MC) and DeepSeek (DS) in terms of accuracy, the translation strategies they use, the causes of translation errors and whether translation students can depend on AI in translating such terms. Analysis of a sample of 205 Arabic folk medical terms containing Om- and Abu by MC and DS showed that 46% of the terms were correctly translated by MC and 66% by DS (أُمُّ الدَّمِ الأَوَّلِيَّة primary aneurysm,أُمُّ الدَّمِ البَطْنِيَّة abdominal aneurysm). MC rendered more literal word-for word translations than DS (16% and 11% respectively). Here أم Om and أبو Abu were literally translated as “mother” and “father” not as a prefix. أبو الرّكَب was translated as “father of the knees” instead of “dengue”, أم التلافيف “mother of folds” instead of omasum psalterium. MC and DS rendered lexical variants (synonyms) as cerebral aneurysm for أُمُّ الدَّمِ الدِّماغِيَّة instead of brain aneurysm. Both MC and DS rendered equivalents with a different word order from the dictionary definition (cavernous carotid aneurysm for أُمُّ الدَّمِ السُّباتِيَّةُ الكَهْفِيَّة instead of caroticocavernous aneurysm). AI translated folk medical terms containing أم Om & أبو Abu with lower accuracy than modern medical terms but higher accuracy rate than expressions of impossibility, Gaza-Israel war terminology, grammatical terms used metaphorically, and zero expressions which are current and commonly used by Arabic speakers. Comparisons with human translation of Om and Abu expressions, strategies used, causes of mistranslations and why DS outperformed MC in translating were made. Users need to understand how to prompt and guide AI models by specifying the context, intent, and audience and should interpret AI outputs critically.

Journal of Medical and Health StudiesVol. 6(4)
Openalex Percentile: Top 87%
Natural Language Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.