<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2019-fill">
    <titleInfo>
        <title>Fill the GAP: Exploiting BERT for Pronoun Resolution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kai-Chou</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Timothy</namePart>
        <namePart type="family">Niven</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tzu</namePart>
        <namePart type="given">Hsuan</namePart>
        <namePart type="family">Chou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hung-Yu</namePart>
        <namePart type="family">Kao</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>In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation. Our method is an ensemble system of BERTs which resolves co-reference in an interaction space. We report four insights from our work: BERT’s representations involve significant redundancy; modeling interaction effects similar to natural language inference models is useful for this task; there is an optimal BERT layer to extract representations for pronoun resolution; and the difference between the attention weights from the pronoun to the candidate entities was highly correlated with the correct label, with interesting implications for future work.</abstract>
    <identifier type="citekey">yang-etal-2019-fill</identifier>
    <identifier type="doi">10.18653/v1/W19-3815</identifier>
    <location>
        <url>https://aclanthology.org/W19-3815</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>102</start>
            <end>106</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fill the GAP: Exploiting BERT for Pronoun Resolution
%A Yang, Kai-Chou
%A Niven, Timothy
%A Chou, Tzu Hsuan
%A Kao, Hung-Yu
%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 yang-etal-2019-fill
%X In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation. Our method is an ensemble system of BERTs which resolves co-reference in an interaction space. We report four insights from our work: BERT’s representations involve significant redundancy; modeling interaction effects similar to natural language inference models is useful for this task; there is an optimal BERT layer to extract representations for pronoun resolution; and the difference between the attention weights from the pronoun to the candidate entities was highly correlated with the correct label, with interesting implications for future work.
%R 10.18653/v1/W19-3815
%U https://aclanthology.org/W19-3815
%U https://doi.org/10.18653/v1/W19-3815
%P 102-106

Markdown (Informal)

[Fill the GAP: Exploiting BERT for Pronoun Resolution](https://aclanthology.org/W19-3815) (Yang et al., GeBNLP 2019)

• Fill the GAP: Exploiting BERT for Pronoun Resolution (Yang et al., GeBNLP 2019)

ACL

• Kai-Chou Yang, Timothy Niven, Tzu Hsuan Chou, and Hung-Yu Kao. 2019. Fill the GAP: Exploiting BERT for Pronoun Resolution. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 102–106, Florence, Italy. Association for Computational Linguistics.