@inproceedings{khair-sawalha-2025-automated,
title = "Automated Translation of Islamic Literature Using Large Language Models: Al-Shamela Library Application",
author = "Khair, Mohammad Mohammad and
Sawalha, Majdi",
editor = "Yagi, Sane and
Yagi, Sane and
Sawalha, Majdi and
Shawar, Bayan Abu and
AlShdaifat, Abdallah T. and
Abbas, Norhan and
Organizers",
booktitle = "Proceedings of the New Horizons in Computational Linguistics for Religious Texts",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clrel-1.5/",
pages = "53--58",
abstract = "Large Language Models (LLM) can be useful tools for translating Islamic literature written in Arabic into several languages, making this complex task technologically feasible, providing high-quality translations, at low cost and high-speed production enabled by parallel computing. We applied LLM-driven translation automation on a diverse corpus of Islamic scholarly works including: the Qur`an, Quranic exegesis (Tafseer), Hadith, and Jurisprudence from the Al-Shamela library. More than 250,000 pages have been translated into English, emphasizing the potential of LLMs to cross language barriers and increase global access to Islamic knowledge. OpenAI`s gpt-4o-mini model was used for the forward translation from Arabic to English with acceptable translation quality. Translation quality validation was achieved by reproducing Arabic text via back-translation from English using both the OpenAI LLM and an independent Anthropic LLM. Correlating the original source Arabic text and the back-translation Arabic text using a vector embedding cosine similarity metric demonstrated comparable translation quality between the two models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khair-sawalha-2025-automated">
<titleInfo>
<title>Automated Translation of Islamic Literature Using Large Language Models: Al-Shamela Library Application</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="family">Khair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the New Horizons in Computational Linguistics for Religious Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sane</namePart>
<namePart type="family">Yagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bayan</namePart>
<namePart type="given">Abu</namePart>
<namePart type="family">Shawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdallah</namePart>
<namePart type="given">T</namePart>
<namePart type="family">AlShdaifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norhan</namePart>
<namePart type="family">Abbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name>
<namePart>Organizers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLM) can be useful tools for translating Islamic literature written in Arabic into several languages, making this complex task technologically feasible, providing high-quality translations, at low cost and high-speed production enabled by parallel computing. We applied LLM-driven translation automation on a diverse corpus of Islamic scholarly works including: the Qur‘an, Quranic exegesis (Tafseer), Hadith, and Jurisprudence from the Al-Shamela library. More than 250,000 pages have been translated into English, emphasizing the potential of LLMs to cross language barriers and increase global access to Islamic knowledge. OpenAI‘s gpt-4o-mini model was used for the forward translation from Arabic to English with acceptable translation quality. Translation quality validation was achieved by reproducing Arabic text via back-translation from English using both the OpenAI LLM and an independent Anthropic LLM. Correlating the original source Arabic text and the back-translation Arabic text using a vector embedding cosine similarity metric demonstrated comparable translation quality between the two models.</abstract>
<identifier type="citekey">khair-sawalha-2025-automated</identifier>
<location>
<url>https://aclanthology.org/2025.clrel-1.5/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>53</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Translation of Islamic Literature Using Large Language Models: Al-Shamela Library Application
%A Khair, Mohammad Mohammad
%A Sawalha, Majdi
%Y Yagi, Sane
%Y Sawalha, Majdi
%Y Shawar, Bayan Abu
%Y AlShdaifat, Abdallah T.
%Y Abbas, Norhan
%E Organizers
%S Proceedings of the New Horizons in Computational Linguistics for Religious Texts
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F khair-sawalha-2025-automated
%X Large Language Models (LLM) can be useful tools for translating Islamic literature written in Arabic into several languages, making this complex task technologically feasible, providing high-quality translations, at low cost and high-speed production enabled by parallel computing. We applied LLM-driven translation automation on a diverse corpus of Islamic scholarly works including: the Qur‘an, Quranic exegesis (Tafseer), Hadith, and Jurisprudence from the Al-Shamela library. More than 250,000 pages have been translated into English, emphasizing the potential of LLMs to cross language barriers and increase global access to Islamic knowledge. OpenAI‘s gpt-4o-mini model was used for the forward translation from Arabic to English with acceptable translation quality. Translation quality validation was achieved by reproducing Arabic text via back-translation from English using both the OpenAI LLM and an independent Anthropic LLM. Correlating the original source Arabic text and the back-translation Arabic text using a vector embedding cosine similarity metric demonstrated comparable translation quality between the two models.
%U https://aclanthology.org/2025.clrel-1.5/
%P 53-58
Markdown (Informal)
[Automated Translation of Islamic Literature Using Large Language Models: Al-Shamela Library Application](https://aclanthology.org/2025.clrel-1.5/) (Khair & Sawalha, CLRel 2025)
ACL