<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-unqovering">
    <titleInfo>
        <title>UNQOVERing Stereotyping Biases via Underspecified Questions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Khashabi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tushar</namePart>
        <namePart type="family">Khot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ashish</namePart>
        <namePart type="family">Sabharwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Srikumar</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <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>While language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. We show that a naive use of model scores can lead to incorrect bias estimates due to two forms of reasoning errors: positional dependence and question independence. We design a formalism that isolates the aforementioned errors. As case studies, we use this metric to analyze four important classes of stereotypes: gender, nationality, ethnicity, and religion. We probe five transformer-based QA models trained on two QA datasets, along with their underlying language models. Our broad study reveals that (1) all these models, with and without fine-tuning, have notable stereotyping biases in these classes; (2) larger models often have higher bias; and (3) the effect of fine-tuning on bias varies strongly with the dataset and the model size.</abstract>
    <identifier type="citekey">li-etal-2020-unqovering</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.311</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.311/</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>3475</start>
            <end>3489</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T UNQOVERing Stereotyping Biases via Underspecified Questions
%A Li, Tao
%A Khashabi, Daniel
%A Khot, Tushar
%A Sabharwal, Ashish
%A Srikumar, Vivek
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F li-etal-2020-unqovering
%X While language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. We show that a naive use of model scores can lead to incorrect bias estimates due to two forms of reasoning errors: positional dependence and question independence. We design a formalism that isolates the aforementioned errors. As case studies, we use this metric to analyze four important classes of stereotypes: gender, nationality, ethnicity, and religion. We probe five transformer-based QA models trained on two QA datasets, along with their underlying language models. Our broad study reveals that (1) all these models, with and without fine-tuning, have notable stereotyping biases in these classes; (2) larger models often have higher bias; and (3) the effect of fine-tuning on bias varies strongly with the dataset and the model size.
%R 10.18653/v1/2020.findings-emnlp.311
%U https://aclanthology.org/2020.findings-emnlp.311/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.311
%P 3475-3489

Markdown (Informal)

[UNQOVERing Stereotyping Biases via Underspecified Questions](https://aclanthology.org/2020.findings-emnlp.311/) (Li et al., Findings 2020)

• UNQOVERing Stereotyping Biases via Underspecified Questions (Li et al., Findings 2020)

ACL

• Tao Li, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Vivek Srikumar. 2020. UNQOVERing Stereotyping Biases via Underspecified Questions. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3475–3489, Online. Association for Computational Linguistics.