<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinan-etal-2020-queens">
    <titleInfo>
        <title>Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Emily</namePart>
        <namePart type="family">Dinan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Angela</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adina</namePart>
        <namePart type="family">Williams</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jack</namePart>
        <namePart type="family">Urbanek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Douwe</namePart>
        <namePart type="family">Kiela</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jason</namePart>
        <namePart type="family">Weston</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Social biases present in data are often directly reflected in the predictions of models trained on that data. We analyze gender bias in dialogue data, and examine how this bias is not only replicated, but is also amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets before selecting the most biased one, the multi-player text-based fantasy adventure dataset LIGHT, as a testbed for bias mitigation techniques. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances, and find that they are particularly effective in combination. We evaluate model performance with a variety of quantitative methods—including the quantity of gendered words, a dialogue safety classifier, and human assessments—all of which show that our models generate less gendered, but equally engaging chit-chat responses.</abstract>
    <identifier type="citekey">dinan-etal-2020-queens</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.656</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.656</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>8173</start>
            <end>8188</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation
%A Dinan, Emily
%A Fan, Angela
%A Williams, Adina
%A Urbanek, Jack
%A Kiela, Douwe
%A Weston, Jason
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F dinan-etal-2020-queens
%X Social biases present in data are often directly reflected in the predictions of models trained on that data. We analyze gender bias in dialogue data, and examine how this bias is not only replicated, but is also amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets before selecting the most biased one, the multi-player text-based fantasy adventure dataset LIGHT, as a testbed for bias mitigation techniques. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances, and find that they are particularly effective in combination. We evaluate model performance with a variety of quantitative methods—including the quantity of gendered words, a dialogue safety classifier, and human assessments—all of which show that our models generate less gendered, but equally engaging chit-chat responses.
%R 10.18653/v1/2020.emnlp-main.656
%U https://aclanthology.org/2020.emnlp-main.656
%U https://doi.org/10.18653/v1/2020.emnlp-main.656
%P 8173-8188

Markdown (Informal)

[Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://aclanthology.org/2020.emnlp-main.656) (Dinan et al., EMNLP 2020)

• Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation (Dinan et al., EMNLP 2020)

ACL

• Emily Dinan, Angela Fan, Adina Williams, Jack Urbanek, Douwe Kiela, and Jason Weston. 2020. Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8173–8188, Online. Association for Computational Linguistics.