@inproceedings{dick-etal-2024-gil,
title = "{GIL}-{GAL}a{D}: Gender Inclusive Language - {G}erman Auto-Assembled Large Database",
author = "Dick, Anna-Katharina and
Drews, Matthias and
Pickard, Valentin and
Pierz, Victoria",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.684/",
pages = "7740--7745",
abstract = "As the need for gender-inclusive language has become a highly debated topic over the years, gendered biases in speech are unfortunately often picked up and propagated by modern language models trained on large amounts of text. While remedial efforts are underway, grammatically gendered languages such as German pose some unique challenges in generating gender-inclusive language for corrective model training or fine-tuning. We assembled GIL-GALaD, a corpus of German gender-inclusive language from different sources such as social media, news articles, public speeches and academic publications. Our corpus includes the most common types of modifications of generic masculine forms of nouns and spans 30 years (1993-2023), containing over 800,000 instances of gender-inclusive language. Tools for corpus usage and extension are to be included in the release. During corpus assembly, we were also able to gain some insights into which types of gender-inclusive language were used in practice throughout the years and across different domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dick-etal-2024-gil">
<titleInfo>
<title>GIL-GALaD: Gender Inclusive Language - German Auto-Assembled Large Database</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna-Katharina</namePart>
<namePart type="family">Dick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Drews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Pickard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Pierz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the need for gender-inclusive language has become a highly debated topic over the years, gendered biases in speech are unfortunately often picked up and propagated by modern language models trained on large amounts of text. While remedial efforts are underway, grammatically gendered languages such as German pose some unique challenges in generating gender-inclusive language for corrective model training or fine-tuning. We assembled GIL-GALaD, a corpus of German gender-inclusive language from different sources such as social media, news articles, public speeches and academic publications. Our corpus includes the most common types of modifications of generic masculine forms of nouns and spans 30 years (1993-2023), containing over 800,000 instances of gender-inclusive language. Tools for corpus usage and extension are to be included in the release. During corpus assembly, we were also able to gain some insights into which types of gender-inclusive language were used in practice throughout the years and across different domains.</abstract>
<identifier type="citekey">dick-etal-2024-gil</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.684/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7740</start>
<end>7745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GIL-GALaD: Gender Inclusive Language - German Auto-Assembled Large Database
%A Dick, Anna-Katharina
%A Drews, Matthias
%A Pickard, Valentin
%A Pierz, Victoria
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dick-etal-2024-gil
%X As the need for gender-inclusive language has become a highly debated topic over the years, gendered biases in speech are unfortunately often picked up and propagated by modern language models trained on large amounts of text. While remedial efforts are underway, grammatically gendered languages such as German pose some unique challenges in generating gender-inclusive language for corrective model training or fine-tuning. We assembled GIL-GALaD, a corpus of German gender-inclusive language from different sources such as social media, news articles, public speeches and academic publications. Our corpus includes the most common types of modifications of generic masculine forms of nouns and spans 30 years (1993-2023), containing over 800,000 instances of gender-inclusive language. Tools for corpus usage and extension are to be included in the release. During corpus assembly, we were also able to gain some insights into which types of gender-inclusive language were used in practice throughout the years and across different domains.
%U https://aclanthology.org/2024.lrec-main.684/
%P 7740-7745
Markdown (Informal)
[GIL-GALaD: Gender Inclusive Language - German Auto-Assembled Large Database](https://aclanthology.org/2024.lrec-main.684/) (Dick et al., LREC-COLING 2024)
ACL