<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chi-etal-2020-finding">
    <titleInfo>
        <title>Finding Universal Grammatical Relations in Multilingual BERT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ethan</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Chi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Hewitt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christopher</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Manning</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</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>Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually. To better understand this overlap, we extend recent work on finding syntactic trees in neural networks’ internal representations to the multilingual setting. We show that subspaces of mBERT representations recover syntactic tree distances in languages other than English, and that these subspaces are approximately shared across languages. Motivated by these results, we present an unsupervised analysis method that provides evidence mBERT learns representations of syntactic dependency labels, in the form of clusters which largely agree with the Universal Dependencies taxonomy. This evidence suggests that even without explicit supervision, multilingual masked language models learn certain linguistic universals.</abstract>
    <identifier type="citekey">chi-etal-2020-finding</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.493</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.493</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>5564</start>
            <end>5577</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Finding Universal Grammatical Relations in Multilingual BERT
%A Chi, Ethan A.
%A Hewitt, John
%A Manning, Christopher D.
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F chi-etal-2020-finding
%X Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually. To better understand this overlap, we extend recent work on finding syntactic trees in neural networks’ internal representations to the multilingual setting. We show that subspaces of mBERT representations recover syntactic tree distances in languages other than English, and that these subspaces are approximately shared across languages. Motivated by these results, we present an unsupervised analysis method that provides evidence mBERT learns representations of syntactic dependency labels, in the form of clusters which largely agree with the Universal Dependencies taxonomy. This evidence suggests that even without explicit supervision, multilingual masked language models learn certain linguistic universals.
%R 10.18653/v1/2020.acl-main.493
%U https://aclanthology.org/2020.acl-main.493
%U https://doi.org/10.18653/v1/2020.acl-main.493
%P 5564-5577

Markdown (Informal)

[Finding Universal Grammatical Relations in Multilingual BERT](https://aclanthology.org/2020.acl-main.493) (Chi et al., ACL 2020)

• Finding Universal Grammatical Relations in Multilingual BERT (Chi et al., ACL 2020)

ACL

• Ethan A. Chi, John Hewitt, and Christopher D. Manning. 2020. Finding Universal Grammatical Relations in Multilingual BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5564–5577, Online. Association for Computational Linguistics.