<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-2019-anonymized">
    <titleInfo>
        <title>Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bo</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Gender Bias in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marta</namePart>
            <namePart type="given">R</namePart>
            <namePart type="family">Costa-jussà</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christian</namePart>
            <namePart type="family">Hardmeier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Will</namePart>
            <namePart type="family">Radford</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kellie</namePart>
            <namePart type="family">Webster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present our 7th place solution to the Gendered Pronoun Resolution challenge, which uses BERT without fine-tuning and a novel augmentation strategy designed for contextual embedding token-level tasks. Our method anonymizes the referent by replacing candidate names with a set of common placeholder names. Besides the usual benefits of effectively increasing training data size, this approach diversifies idiosyncratic information embedded in names. Using same set of common first names can also help the model recognize names better, shorten token length, and remove gender and regional biases associated with names. The system scored 0.1947 log loss in stage 2, where the augmentation contributed to an improvements of 0.04. Post-competition analysis shows that, when using different embedding layers, the system scores 0.1799 which would be third place.</abstract>
    <identifier type="citekey">liu-2019-anonymized</identifier>
    <identifier type="doi">10.18653/v1/W19-3818</identifier>
    <location>
        <url>https://aclanthology.org/W19-3818</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>120</start>
            <end>125</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge
%A Liu, Bo
%Y Costa-jussà, Marta R.
%Y Hardmeier, Christian
%Y Radford, Will
%Y Webster, Kellie
%S Proceedings of the First Workshop on Gender Bias in Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F liu-2019-anonymized
%X We present our 7th place solution to the Gendered Pronoun Resolution challenge, which uses BERT without fine-tuning and a novel augmentation strategy designed for contextual embedding token-level tasks. Our method anonymizes the referent by replacing candidate names with a set of common placeholder names. Besides the usual benefits of effectively increasing training data size, this approach diversifies idiosyncratic information embedded in names. Using same set of common first names can also help the model recognize names better, shorten token length, and remove gender and regional biases associated with names. The system scored 0.1947 log loss in stage 2, where the augmentation contributed to an improvements of 0.04. Post-competition analysis shows that, when using different embedding layers, the system scores 0.1799 which would be third place.
%R 10.18653/v1/W19-3818
%U https://aclanthology.org/W19-3818
%U https://doi.org/10.18653/v1/W19-3818
%P 120-125

Markdown (Informal)

[Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge](https://aclanthology.org/W19-3818) (Liu, GeBNLP 2019)

• Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge (Liu, GeBNLP 2019)

ACL

• Bo Liu. 2019. Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 120–125, Florence, Italy. Association for Computational Linguistics.