@inproceedings{youssef-etal-2026-al,
title = "Al-Warraq at {AR}-{MS} {NAKBA}-{NLP} 2026: Adapting Vision-Language and Transformer Models for Automatic Manuscript {OCR}/{HTR}",
author = "Youssef, Ahmad Edris and
Faris, Aya Hafiz and
Hamood, Alhasan and
Kamil, Zainab and
Alqasem, Jana and
hamed{''}, SARA Ali",
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-1.26/",
doi = "10.63317/2fv6385csb36",
pages = "191--195",
abstract = "We present our submission to the NAKBA NLP 2026 Automatic Manuscript OCR/HTR shared task on Arabic manuscripts. The task aims to transcribe manuscript line images into machine-readable Arabic text. Our approach followed an iterative pipeline including model selection, training, error analysis, test-time augmentation, and postprocessing. After evaluating several OCR/HTR models, we selected and trained the most suitable model on the provided manuscript line images and transcriptions. Error analysis showed better character-level performance than word-level performance, which motivated the use of test-time augmentation and text cleaning to improve robustness. The final system achieved a CER of 0.1142 and a WER of 0.378, placing fifth in the shared task. These results show that simple but targeted improvements can support effective Arabic manuscript transcription."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="youssef-etal-2026-al">
<titleInfo>
<title>Al-Warraq at AR-MS NAKBA-NLP 2026: Adapting Vision-Language and Transformer Models for Automatic Manuscript OCR/HTR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="given">Edris</namePart>
<namePart type="family">Youssef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aya</namePart>
<namePart type="given">Hafiz</namePart>
<namePart type="family">Faris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alhasan</namePart>
<namePart type="family">Hamood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zainab</namePart>
<namePart type="family">Kamil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Alqasem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SARA</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">hamed”</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>We present our submission to the NAKBA NLP 2026 Automatic Manuscript OCR/HTR shared task on Arabic manuscripts. The task aims to transcribe manuscript line images into machine-readable Arabic text. Our approach followed an iterative pipeline including model selection, training, error analysis, test-time augmentation, and postprocessing. After evaluating several OCR/HTR models, we selected and trained the most suitable model on the provided manuscript line images and transcriptions. Error analysis showed better character-level performance than word-level performance, which motivated the use of test-time augmentation and text cleaning to improve robustness. The final system achieved a CER of 0.1142 and a WER of 0.378, placing fifth in the shared task. These results show that simple but targeted improvements can support effective Arabic manuscript transcription.</abstract>
<identifier type="citekey">youssef-etal-2026-al</identifier>
<identifier type="doi">10.63317/2fv6385csb36</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.26/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>191</start>
<end>195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Al-Warraq at AR-MS NAKBA-NLP 2026: Adapting Vision-Language and Transformer Models for Automatic Manuscript OCR/HTR
%A Youssef, Ahmad Edris
%A Faris, Aya Hafiz
%A Hamood, Alhasan
%A Kamil, Zainab
%A Alqasem, Jana
%A hamed”, SARA Ali
%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 youssef-etal-2026-al
%X We present our submission to the NAKBA NLP 2026 Automatic Manuscript OCR/HTR shared task on Arabic manuscripts. The task aims to transcribe manuscript line images into machine-readable Arabic text. Our approach followed an iterative pipeline including model selection, training, error analysis, test-time augmentation, and postprocessing. After evaluating several OCR/HTR models, we selected and trained the most suitable model on the provided manuscript line images and transcriptions. Error analysis showed better character-level performance than word-level performance, which motivated the use of test-time augmentation and text cleaning to improve robustness. The final system achieved a CER of 0.1142 and a WER of 0.378, placing fifth in the shared task. These results show that simple but targeted improvements can support effective Arabic manuscript transcription.
%R 10.63317/2fv6385csb36
%U https://aclanthology.org/2026.nakbanlp-1.26/
%U https://doi.org/10.63317/2fv6385csb36
%P 191-195
Markdown (Informal)
[Al-Warraq at AR-MS NAKBA-NLP 2026: Adapting Vision-Language and Transformer Models for Automatic Manuscript OCR/HTR](https://aclanthology.org/2026.nakbanlp-1.26/) (Youssef et al., NakbaNLP 2026)
ACL