@inproceedings{shaheen-etal-2026-subwords,
title = "From Subwords to Pixels: Evaluating Text Representations for {A}rabic Machine Translation",
author = "Shaheen, Abdelrahman and
Abbas, Mohamed and
Truckova, Tereza and
Kementchedjhieva, Yova and
Alhafni, Bashar",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.19/",
pages = "263--288",
ISBN = "979-8-89176-473-6",
abstract = "Subword tokenization underpins modern neural NLP but can be suboptimal for morphologically rich languages with substantial orthographic variation. In this paper, we compare vocabulary-based and vocabulary-free representations for Arabic-to-English machine translation, including subword, byte-level, and pixel-level approaches. Across 35 evaluation sets spanning Modern Standard Arabic (MSA) and 18 dialects, all approaches achieve comparable translation performance with sufficient supervision. While subword models perform best with limited MSA pretraining data, differences diminish with scale and dialect-specific fine-tuning. Pixel-based models further exhibit the greatest robustness to unseen orthographic variation and provide the highest training and inference throughput. We make our code and models publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shaheen-etal-2026-subwords">
<titleInfo>
<title>From Subwords to Pixels: Evaluating Text Representations for Arabic Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Shaheen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tereza</namePart>
<namePart type="family">Truckova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Subword tokenization underpins modern neural NLP but can be suboptimal for morphologically rich languages with substantial orthographic variation. In this paper, we compare vocabulary-based and vocabulary-free representations for Arabic-to-English machine translation, including subword, byte-level, and pixel-level approaches. Across 35 evaluation sets spanning Modern Standard Arabic (MSA) and 18 dialects, all approaches achieve comparable translation performance with sufficient supervision. While subword models perform best with limited MSA pretraining data, differences diminish with scale and dialect-specific fine-tuning. Pixel-based models further exhibit the greatest robustness to unseen orthographic variation and provide the highest training and inference throughput. We make our code and models publicly available.</abstract>
<identifier type="citekey">shaheen-etal-2026-subwords</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>263</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Subwords to Pixels: Evaluating Text Representations for Arabic Machine Translation
%A Shaheen, Abdelrahman
%A Abbas, Mohamed
%A Truckova, Tereza
%A Kementchedjhieva, Yova
%A Alhafni, Bashar
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F shaheen-etal-2026-subwords
%X Subword tokenization underpins modern neural NLP but can be suboptimal for morphologically rich languages with substantial orthographic variation. In this paper, we compare vocabulary-based and vocabulary-free representations for Arabic-to-English machine translation, including subword, byte-level, and pixel-level approaches. Across 35 evaluation sets spanning Modern Standard Arabic (MSA) and 18 dialects, all approaches achieve comparable translation performance with sufficient supervision. While subword models perform best with limited MSA pretraining data, differences diminish with scale and dialect-specific fine-tuning. Pixel-based models further exhibit the greatest robustness to unseen orthographic variation and provide the highest training and inference throughput. We make our code and models publicly available.
%U https://aclanthology.org/2026.arabicnlp-main.19/
%P 263-288
Markdown (Informal)
[From Subwords to Pixels: Evaluating Text Representations for Arabic Machine Translation](https://aclanthology.org/2026.arabicnlp-main.19/) (Shaheen et al., ArabicNLP 2026)
ACL