<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-cho-2019-bert">
    <titleInfo>
        <title>BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyunghyun</namePart>
        <namePart type="family">Cho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Antoine</namePart>
            <namePart type="family">Bosselut</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asli</namePart>
            <namePart type="family">Celikyilmaz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marjan</namePart>
            <namePart type="family">Ghazvininejad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Srinivasan</namePart>
            <namePart type="family">Iyer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Urvashi</namePart>
            <namePart type="family">Khandelwal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hannah</namePart>
            <namePart type="family">Rashkin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thomas</namePart>
            <namePart type="family">Wolf</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high quality, fluent generations. Compared to the generations of a traditional left-to-right language model, BERT generates sentences that are more diverse but of slightly worse quality.</abstract>
    <identifier type="citekey">wang-cho-2019-bert</identifier>
    <identifier type="doi">10.18653/v1/W19-2304</identifier>
    <location>
        <url>https://aclanthology.org/W19-2304/</url>
    </location>
    <part>
        <date>2019-06</date>
        <extent unit="page">
            <start>30</start>
            <end>36</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model
%A Wang, Alex
%A Cho, Kyunghyun
%Y Bosselut, Antoine
%Y Celikyilmaz, Asli
%Y Ghazvininejad, Marjan
%Y Iyer, Srinivasan
%Y Khandelwal, Urvashi
%Y Rashkin, Hannah
%Y Wolf, Thomas
%S Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F wang-cho-2019-bert
%X We show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high quality, fluent generations. Compared to the generations of a traditional left-to-right language model, BERT generates sentences that are more diverse but of slightly worse quality.
%R 10.18653/v1/W19-2304
%U https://aclanthology.org/W19-2304/
%U https://doi.org/10.18653/v1/W19-2304
%P 30-36

Markdown (Informal)

[BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://aclanthology.org/W19-2304/) (Wang & Cho, NAACL 2019)

• BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model (Wang & Cho, NAACL 2019)

ACL

• Alex Wang and Kyunghyun Cho. 2019. BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pages 30–36, Minneapolis, Minnesota. Association for Computational Linguistics.