@inproceedings{al-desouky-2026-latent,
title = "Latent Narratives at {AR}-{MS} {N}akba{NLP} 2026: Reducing Character Errors in {A}rabic Manuscript Transcription: A {CER} Oriented System",
author = "Al desouky, Sara Abdulmonem",
editor = "Jarrar, Mustafa and
El-Haj, Mo and
Haddad, Amal and
Atiani, Serin and
Abudalfa, Shadi and
Regier, Terry and
Rayson, Paul and
Sima{'}an, Khalil and
Mansour, Camille",
booktitle = "Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nakbanlp-1.43/",
doi = "10.63317/3gkghprpz2sb",
pages = "279--283",
abstract = "Historic Arabic handwritten texts present significant challenges due to varied handwriting styles, cursive structure, diverse diacritics, and inconsistent character and word sizes. In this work, we introduce Historic-Arabic-OCR, a vision-language OCR system built upon Qari-OCR, which itself is based on Qwen2-VL-2B-Instruct, and further fine- tuned using Low-Rank Adaptation (LoRA) for Arabic manuscript transcription. The proposed approach incorporates contrast enhancement using CLAHE and deterministic decoding strategies to reduce character-level errors. Our model achieves competitive performance, with a Word Error Rate (WER) of 0.28 and a Character Error Rate (CER) of 0.10 on historical Arabic texts, including low-resolution images. The final submitted system uses CLAHE prepro- cessing with deterministic greedy decoding to minimize character-level errors. Keywords: Arabic OCR, Vision-Language Models, Qwen2-VL, LoRA, CER Optimization"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-desouky-2026-latent">
<titleInfo>
<title>Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="given">Abdulmonem</namePart>
<namePart type="family">Al desouky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serin</namePart>
<namePart type="family">Atiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Abudalfa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Regier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Sima’an</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Historic Arabic handwritten texts present significant challenges due to varied handwriting styles, cursive structure, diverse diacritics, and inconsistent character and word sizes. In this work, we introduce Historic-Arabic-OCR, a vision-language OCR system built upon Qari-OCR, which itself is based on Qwen2-VL-2B-Instruct, and further fine- tuned using Low-Rank Adaptation (LoRA) for Arabic manuscript transcription. The proposed approach incorporates contrast enhancement using CLAHE and deterministic decoding strategies to reduce character-level errors. Our model achieves competitive performance, with a Word Error Rate (WER) of 0.28 and a Character Error Rate (CER) of 0.10 on historical Arabic texts, including low-resolution images. The final submitted system uses CLAHE prepro- cessing with deterministic greedy decoding to minimize character-level errors. Keywords: Arabic OCR, Vision-Language Models, Qwen2-VL, LoRA, CER Optimization</abstract>
<identifier type="citekey">al-desouky-2026-latent</identifier>
<identifier type="doi">10.63317/3gkghprpz2sb</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.43/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>279</start>
<end>283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System
%A Al desouky, Sara Abdulmonem
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Haddad, Amal
%Y Atiani, Serin
%Y Abudalfa, Shadi
%Y Regier, Terry
%Y Rayson, Paul
%Y Sima’an, Khalil
%Y Mansour, Camille
%S Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F al-desouky-2026-latent
%X Historic Arabic handwritten texts present significant challenges due to varied handwriting styles, cursive structure, diverse diacritics, and inconsistent character and word sizes. In this work, we introduce Historic-Arabic-OCR, a vision-language OCR system built upon Qari-OCR, which itself is based on Qwen2-VL-2B-Instruct, and further fine- tuned using Low-Rank Adaptation (LoRA) for Arabic manuscript transcription. The proposed approach incorporates contrast enhancement using CLAHE and deterministic decoding strategies to reduce character-level errors. Our model achieves competitive performance, with a Word Error Rate (WER) of 0.28 and a Character Error Rate (CER) of 0.10 on historical Arabic texts, including low-resolution images. The final submitted system uses CLAHE prepro- cessing with deterministic greedy decoding to minimize character-level errors. Keywords: Arabic OCR, Vision-Language Models, Qwen2-VL, LoRA, CER Optimization
%R 10.63317/3gkghprpz2sb
%U https://aclanthology.org/2026.nakbanlp-1.43/
%U https://doi.org/10.63317/3gkghprpz2sb
%P 279-283
Markdown (Informal)
[Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System](https://aclanthology.org/2026.nakbanlp-1.43/) (Al desouky, NakbaNLP 2026)
ACL