@inproceedings{kappl-etal-2026-deval,
title = "{DE}val-{MT}: An Intersectional Gender Bias Evaluation Framework for {G}erman Machine Translation",
author = "Kappl, Michelle and
Schreiber, Leon and
Hillmann, Stefan",
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-1.13/",
pages = "181--192",
ISBN = "979-8-89176-447-7",
abstract = "Machine translation systems can reproduce gender bias, but most evaluation resources are limited to English as the source language. We introduce DEval-MT, a template-based framework for evaluating gender bias in German-source machine translation, comprising 6,618 sentences across six sentence styles with an intersectional template design that can be extended with additional demographic attributes and support for nonbinary neopronouns. Alongside it, we provide a Python package for translation, alignment, gender prediction, and analysis. Evaluating six different MT systems on seven target languages using this dataset and pipeline, we find evidence of representational harms across multiple demographic groups."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kappl-etal-2026-deval">
<titleInfo>
<title>DEval-MT: An Intersectional Gender Bias Evaluation Framework for German Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Kappl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Schreiber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Hillmann</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>Machine translation systems can reproduce gender bias, but most evaluation resources are limited to English as the source language. We introduce DEval-MT, a template-based framework for evaluating gender bias in German-source machine translation, comprising 6,618 sentences across six sentence styles with an intersectional template design that can be extended with additional demographic attributes and support for nonbinary neopronouns. Alongside it, we provide a Python package for translation, alignment, gender prediction, and analysis. Evaluating six different MT systems on seven target languages using this dataset and pipeline, we find evidence of representational harms across multiple demographic groups.</abstract>
<identifier type="citekey">kappl-etal-2026-deval</identifier>
<location>
<url>https://aclanthology.org/2026.gebnlp-1.13/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>181</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DEval-MT: An Intersectional Gender Bias Evaluation Framework for German Machine Translation
%A Kappl, Michelle
%A Schreiber, Leon
%A Hillmann, Stefan
%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 kappl-etal-2026-deval
%X Machine translation systems can reproduce gender bias, but most evaluation resources are limited to English as the source language. We introduce DEval-MT, a template-based framework for evaluating gender bias in German-source machine translation, comprising 6,618 sentences across six sentence styles with an intersectional template design that can be extended with additional demographic attributes and support for nonbinary neopronouns. Alongside it, we provide a Python package for translation, alignment, gender prediction, and analysis. Evaluating six different MT systems on seven target languages using this dataset and pipeline, we find evidence of representational harms across multiple demographic groups.
%U https://aclanthology.org/2026.gebnlp-1.13/
%P 181-192
Markdown (Informal)
[DEval-MT: An Intersectional Gender Bias Evaluation Framework for German Machine Translation](https://aclanthology.org/2026.gebnlp-1.13/) (Kappl et al., GeBNLP 2026)
ACL