<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="conti-wisniewski-2023-using">
    <titleInfo>
        <title>Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lina</namePart>
        <namePart type="family">Conti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guillaume</namePart>
        <namePart type="family">Wisniewski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <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">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models discover linguistic properties of words, such as gender, as well as the rules governing their usage. We propose to use an artificial corpus generated by a PCFG based on French to precisely control the gender distribution in the training data and determine under which conditions a model correctly captures gender information or, on the contrary, appears gender-biased.</abstract>
    <identifier type="citekey">conti-wisniewski-2023-using</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.641</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.641</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>10362</start>
            <end>10371</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models
%A Conti, Lina
%A Wisniewski, Guillaume
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F conti-wisniewski-2023-using
%X Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models discover linguistic properties of words, such as gender, as well as the rules governing their usage. We propose to use an artificial corpus generated by a PCFG based on French to precisely control the gender distribution in the training data and determine under which conditions a model correctly captures gender information or, on the contrary, appears gender-biased.
%R 10.18653/v1/2023.emnlp-main.641
%U https://aclanthology.org/2023.emnlp-main.641
%U https://doi.org/10.18653/v1/2023.emnlp-main.641
%P 10362-10371

Markdown (Informal)

[Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models](https://aclanthology.org/2023.emnlp-main.641) (Conti & Wisniewski, EMNLP 2023)

• Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models (Conti & Wisniewski, EMNLP 2023)

ACL

• Lina Conti and Guillaume Wisniewski. 2023. Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10362–10371, Singapore. Association for Computational Linguistics.