<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nangia-etal-2020-crows">
    <titleInfo>
        <title>CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikita</namePart>
        <namePart type="family">Nangia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Clara</namePart>
        <namePart type="family">Vania</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rasika</namePart>
        <namePart type="family">Bhalerao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samuel</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Bowman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-nov</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with two sentences: one that is more stereotyping and another that is less stereotyping. The data focuses on stereotypes about historically disadvantaged groups and contrasts them with advantaged groups. We find that all three of the widely-used MLMs we evaluate substantially favor sentences that express stereotypes in every category in CrowS-Pairs. As work on building less biased models advances, this dataset can be used as a benchmark to evaluate progress.</abstract>
    <identifier type="citekey">nangia-etal-2020-crows</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.154</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.154</url>
    </location>
    <part>
        <date>2020-nov</date>
        <extent unit="page">
            <start>1953</start>
            <end>1967</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
%A Nangia, Nikita
%A Vania, Clara
%A Bhalerao, Rasika
%A Bowman, Samuel R.
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F nangia-etal-2020-crows
%X Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with two sentences: one that is more stereotyping and another that is less stereotyping. The data focuses on stereotypes about historically disadvantaged groups and contrasts them with advantaged groups. We find that all three of the widely-used MLMs we evaluate substantially favor sentences that express stereotypes in every category in CrowS-Pairs. As work on building less biased models advances, this dataset can be used as a benchmark to evaluate progress.
%R 10.18653/v1/2020.emnlp-main.154
%U https://aclanthology.org/2020.emnlp-main.154
%U https://doi.org/10.18653/v1/2020.emnlp-main.154
%P 1953-1967

Markdown (Informal)

[CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://aclanthology.org/2020.emnlp-main.154) (Nangia et al., EMNLP 2020)

• CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models (Nangia et al., EMNLP 2020)

ACL

• Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020. CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1953–1967, Online. Association for Computational Linguistics.