<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amrhein-etal-2023-exploiting">
    <titleInfo>
        <title>Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chantal</namePart>
        <namePart type="family">Amrhein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Florian</namePart>
        <namePart type="family">Schottmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samuel</namePart>
        <namePart type="family">Läubli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data through linguistic rules. However, this approach is not practical for languages with more complex morphology than English. We hypothesise that creating training data in the reverse direction, i.e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English. To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. Our approach allows us to train a rewriting model for German without the need for elaborate handcrafted rules. The outputs of this model increased gender-fairness as shown in a human evaluation study.</abstract>
    <identifier type="citekey">amrhein-etal-2023-exploiting</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.246</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.246</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>4486</start>
            <end>4506</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
%A Amrhein, Chantal
%A Schottmann, Florian
%A Sennrich, Rico
%A Läubli, Samuel
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F amrhein-etal-2023-exploiting
%X Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data through linguistic rules. However, this approach is not practical for languages with more complex morphology than English. We hypothesise that creating training data in the reverse direction, i.e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English. To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. Our approach allows us to train a rewriting model for German without the need for elaborate handcrafted rules. The outputs of this model increased gender-fairness as shown in a human evaluation study.
%R 10.18653/v1/2023.acl-long.246
%U https://aclanthology.org/2023.acl-long.246
%U https://doi.org/10.18653/v1/2023.acl-long.246
%P 4486-4506

Markdown (Informal)

[Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model](https://aclanthology.org/2023.acl-long.246) (Amrhein et al., ACL 2023)

• Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model (Amrhein et al., ACL 2023)

ACL

• Chantal Amrhein, Florian Schottmann, Rico Sennrich, and Samuel Läubli. 2023. Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4486–4506, Toronto, Canada. Association for Computational Linguistics.