@inproceedings{juhaysh-etal-2026-oblevit,
title = "Oblevit at {AR}-{MS} {NAKBA} {NLP} 2026 Subtask 2: Hybrid {CNN}{--}{B}i{LSTM}{--}{CTC} Framework with Linguistic Refinement for {A}rabic Handwritten Manuscript Recognition",
author = "Juhaysh, Reem and
Abusonoun, Abuelgasim Sami and
Ayad, Sara",
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-1.35/",
doi = "10.63317/5nwur655ha5k",
pages = "234--238",
abstract = "Arabic handwritten manuscript recognition is challenging due to the cursive nature of the script, dot ambiguity, and document degradation. In this work, we propose an end-to-end OCR system based on a CNN{--}BiLSTM{--}CTC architecture. The model extracts visual features, captures sequential dependencies, and performs alignment-free training. Arabic-specific decoding and post-processing techniques are applied to reduce character and spacing errors. Experimental results show competitive performance in recognizing complex handwritten Arabic text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="juhaysh-etal-2026-oblevit">
<titleInfo>
<title>Oblevit at AR-MS NAKBA NLP 2026 Subtask 2: Hybrid CNN–BiLSTM–CTC Framework with Linguistic Refinement for Arabic Handwritten Manuscript Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Juhaysh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abuelgasim</namePart>
<namePart type="given">Sami</namePart>
<namePart type="family">Abusonoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Ayad</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>Arabic handwritten manuscript recognition is challenging due to the cursive nature of the script, dot ambiguity, and document degradation. In this work, we propose an end-to-end OCR system based on a CNN–BiLSTM–CTC architecture. The model extracts visual features, captures sequential dependencies, and performs alignment-free training. Arabic-specific decoding and post-processing techniques are applied to reduce character and spacing errors. Experimental results show competitive performance in recognizing complex handwritten Arabic text.</abstract>
<identifier type="citekey">juhaysh-etal-2026-oblevit</identifier>
<identifier type="doi">10.63317/5nwur655ha5k</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.35/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>234</start>
<end>238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Oblevit at AR-MS NAKBA NLP 2026 Subtask 2: Hybrid CNN–BiLSTM–CTC Framework with Linguistic Refinement for Arabic Handwritten Manuscript Recognition
%A Juhaysh, Reem
%A Abusonoun, Abuelgasim Sami
%A Ayad, Sara
%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 juhaysh-etal-2026-oblevit
%X Arabic handwritten manuscript recognition is challenging due to the cursive nature of the script, dot ambiguity, and document degradation. In this work, we propose an end-to-end OCR system based on a CNN–BiLSTM–CTC architecture. The model extracts visual features, captures sequential dependencies, and performs alignment-free training. Arabic-specific decoding and post-processing techniques are applied to reduce character and spacing errors. Experimental results show competitive performance in recognizing complex handwritten Arabic text.
%R 10.63317/5nwur655ha5k
%U https://aclanthology.org/2026.nakbanlp-1.35/
%U https://doi.org/10.63317/5nwur655ha5k
%P 234-238
Markdown (Informal)
[Oblevit at AR-MS NAKBA NLP 2026 Subtask 2: Hybrid CNN–BiLSTM–CTC Framework with Linguistic Refinement for Arabic Handwritten Manuscript Recognition](https://aclanthology.org/2026.nakbanlp-1.35/) (Juhaysh et al., NakbaNLP 2026)
ACL