@inproceedings{alam-etal-2025-automated,
title = "Automated Authentication of {Q}uranic Verses Using {BERT} (Bidirectional Encoder Representations from Transformers) based Language Models",
author = "Alam, Khubaib Amjad and
Khalid, Maryam and
Ali, Syed Ahmed and
Mahmood, Haroon and
Shafi, Qaisar and
Haroon, Muhammad and
Haider, Zulqarnain",
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-1.6/",
pages = "59--66",
abstract = "The proliferation of Quranic content on digital platforms, including websites and social media, has brought about significant challenges in verifying the authenticity of Quranic verses. The inherent complexity of the Arabic language, with its rich morphology, syntax, and semantics, makes traditional text-processing techniques inadequate for robust authentication. This paper addresses this problem by leveraging state-of-the-art transformer-based Language models tailored for Arabic text processing. Our approach involves fine-tuning three transformer architectures BERT-Base-Arabic, AraBERT, and MarBERT on a curated dataset containing both authentic and non-authentic verses. Non-authentic examples were created using sentence-BERT, which applies cosine similarity to introduce subtle modifications. Comprehensive experiments were conducted to evaluate the performance of the models. Among the three candidate models, MarBERT, which is specifically designed for handling Arabic dialects demonstrated superior performance, achieving an F1-score of 93.80{\%}. BERT-Base-Arabic also showed competitive F1 score of 92.90{\%} reflecting its robust understanding of Arabic text. The findings underscore the potential of transformer-based models in addressing linguistic complexities inherent in Quranic text and pave the way for developing automated, reliable tools for Quranic verse authentication in the digital era."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alam-etal-2025-automated">
<titleInfo>
<title>Automated Authentication of Quranic Verses Using BERT (Bidirectional Encoder Representations from Transformers) based Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khubaib</namePart>
<namePart type="given">Amjad</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Khalid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haroon</namePart>
<namePart type="family">Mahmood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qaisar</namePart>
<namePart type="family">Shafi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Haroon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulqarnain</namePart>
<namePart type="family">Haider</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>The proliferation of Quranic content on digital platforms, including websites and social media, has brought about significant challenges in verifying the authenticity of Quranic verses. The inherent complexity of the Arabic language, with its rich morphology, syntax, and semantics, makes traditional text-processing techniques inadequate for robust authentication. This paper addresses this problem by leveraging state-of-the-art transformer-based Language models tailored for Arabic text processing. Our approach involves fine-tuning three transformer architectures BERT-Base-Arabic, AraBERT, and MarBERT on a curated dataset containing both authentic and non-authentic verses. Non-authentic examples were created using sentence-BERT, which applies cosine similarity to introduce subtle modifications. Comprehensive experiments were conducted to evaluate the performance of the models. Among the three candidate models, MarBERT, which is specifically designed for handling Arabic dialects demonstrated superior performance, achieving an F1-score of 93.80%. BERT-Base-Arabic also showed competitive F1 score of 92.90% reflecting its robust understanding of Arabic text. The findings underscore the potential of transformer-based models in addressing linguistic complexities inherent in Quranic text and pave the way for developing automated, reliable tools for Quranic verse authentication in the digital era.</abstract>
<identifier type="citekey">alam-etal-2025-automated</identifier>
<location>
<url>https://aclanthology.org/2025.clrel-1.6/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>59</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Authentication of Quranic Verses Using BERT (Bidirectional Encoder Representations from Transformers) based Language Models
%A Alam, Khubaib Amjad
%A Khalid, Maryam
%A Ali, Syed Ahmed
%A Mahmood, Haroon
%A Shafi, Qaisar
%A Haroon, Muhammad
%A Haider, Zulqarnain
%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 alam-etal-2025-automated
%X The proliferation of Quranic content on digital platforms, including websites and social media, has brought about significant challenges in verifying the authenticity of Quranic verses. The inherent complexity of the Arabic language, with its rich morphology, syntax, and semantics, makes traditional text-processing techniques inadequate for robust authentication. This paper addresses this problem by leveraging state-of-the-art transformer-based Language models tailored for Arabic text processing. Our approach involves fine-tuning three transformer architectures BERT-Base-Arabic, AraBERT, and MarBERT on a curated dataset containing both authentic and non-authentic verses. Non-authentic examples were created using sentence-BERT, which applies cosine similarity to introduce subtle modifications. Comprehensive experiments were conducted to evaluate the performance of the models. Among the three candidate models, MarBERT, which is specifically designed for handling Arabic dialects demonstrated superior performance, achieving an F1-score of 93.80%. BERT-Base-Arabic also showed competitive F1 score of 92.90% reflecting its robust understanding of Arabic text. The findings underscore the potential of transformer-based models in addressing linguistic complexities inherent in Quranic text and pave the way for developing automated, reliable tools for Quranic verse authentication in the digital era.
%U https://aclanthology.org/2025.clrel-1.6/
%P 59-66
Markdown (Informal)
[Automated Authentication of Quranic Verses Using BERT (Bidirectional Encoder Representations from Transformers) based Language Models](https://aclanthology.org/2025.clrel-1.6/) (Alam et al., CLRel 2025)
ACL