@inproceedings{zaghouani-2026-language,
title = "When the Language Must Choose: A Position on Gender Bias Evaluation for {A}rabic {NLP}",
author = "Zaghouani, Wajdi",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Sta{\'n}czak, Karolina and
Nozza, Debora and
Attanasio, Giuseppe and
Neplenbroek, Vera and
Hardmeier, Christian",
booktitle = "Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing ({G}e{BNLP})",
month = nov,
year = "2026",
address = "Hengqin, China (remote)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gebnlp-1.12/",
pages = "173--180",
ISBN = "979-8-89176-447-7",
abstract = "Standard English-centric gender bias evaluation provides incomplete coverage of Arabic because Arabic grammar obligates gender choices on verbs, adjectives, pronouns, and nouns. Translating occupation-noun tests or English rewriting benchmarks to Arabic ignores the grammatical forcing that is central to the problem. We argue evaluation for grammatical gender languages requires language-specific extensions starting from the morphology that forces a choice, naming who is affected by the default form chosen, and then assessing whether a system-internal fix helped. Drawing on Arabic Parallel Gender Corpus work, WinoMT, and gender rewriting tools, we offer a protocol for transparent evaluation: name the linguistic condition, including construction type, grammatical person, and number; name the default (the masculine-leaning BLEU gaps); separate linguistic gender from social gender; and do not flatten intersectionality. Arabic evaluation work should be built from Arabic grammar, not adapted from English methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-2026-language">
<titleInfo>
<title>When the Language Must Choose: A Position on Gender Bias Evaluation for Arabic NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Stańczak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Neplenbroek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China (remote)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-447-7</identifier>
</relatedItem>
<abstract>Standard English-centric gender bias evaluation provides incomplete coverage of Arabic because Arabic grammar obligates gender choices on verbs, adjectives, pronouns, and nouns. Translating occupation-noun tests or English rewriting benchmarks to Arabic ignores the grammatical forcing that is central to the problem. We argue evaluation for grammatical gender languages requires language-specific extensions starting from the morphology that forces a choice, naming who is affected by the default form chosen, and then assessing whether a system-internal fix helped. Drawing on Arabic Parallel Gender Corpus work, WinoMT, and gender rewriting tools, we offer a protocol for transparent evaluation: name the linguistic condition, including construction type, grammatical person, and number; name the default (the masculine-leaning BLEU gaps); separate linguistic gender from social gender; and do not flatten intersectionality. Arabic evaluation work should be built from Arabic grammar, not adapted from English methods.</abstract>
<identifier type="citekey">zaghouani-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.gebnlp-1.12/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>173</start>
<end>180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When the Language Must Choose: A Position on Gender Bias Evaluation for Arabic NLP
%A Zaghouani, Wajdi
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Stańczak, Karolina
%Y Nozza, Debora
%Y Attanasio, Giuseppe
%Y Neplenbroek, Vera
%Y Hardmeier, Christian
%S Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China (remote)
%@ 979-8-89176-447-7
%F zaghouani-2026-language
%X Standard English-centric gender bias evaluation provides incomplete coverage of Arabic because Arabic grammar obligates gender choices on verbs, adjectives, pronouns, and nouns. Translating occupation-noun tests or English rewriting benchmarks to Arabic ignores the grammatical forcing that is central to the problem. We argue evaluation for grammatical gender languages requires language-specific extensions starting from the morphology that forces a choice, naming who is affected by the default form chosen, and then assessing whether a system-internal fix helped. Drawing on Arabic Parallel Gender Corpus work, WinoMT, and gender rewriting tools, we offer a protocol for transparent evaluation: name the linguistic condition, including construction type, grammatical person, and number; name the default (the masculine-leaning BLEU gaps); separate linguistic gender from social gender; and do not flatten intersectionality. Arabic evaluation work should be built from Arabic grammar, not adapted from English methods.
%U https://aclanthology.org/2026.gebnlp-1.12/
%P 173-180
Markdown (Informal)
[When the Language Must Choose: A Position on Gender Bias Evaluation for Arabic NLP](https://aclanthology.org/2026.gebnlp-1.12/) (Zaghouani, GeBNLP 2026)
ACL