<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonen-etal-2020-greek">
    <titleInfo>
        <title>It‘s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hila</namePart>
        <namePart type="family">Gonen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shauli</namePart>
        <namePart type="family">Ravfogel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanai</namePart>
        <namePart type="family">Elazar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoav</namePart>
        <namePart type="family">Goldberg</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>Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Afra</namePart>
            <namePart type="family">Alishahi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yonatan</namePart>
            <namePart type="family">Belinkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Grzegorz</namePart>
            <namePart type="family">Chrupała</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dieuwke</namePart>
            <namePart type="family">Hupkes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yuval</namePart>
            <namePart type="family">Pinter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hassan</namePart>
            <namePart type="family">Sajjad</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 works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple methods that expose remarkable translation capabilities with no fine-tuning. The results suggest that most of this information is encoded in a non-linear way, while some of it can also be recovered with purely linear tools. As part of our analysis, we test the hypothesis that mBERT learns representations which contain both a language-encoding component and an abstract, cross-lingual component, and explicitly identify an empirical language-identity subspace within mBERT representations.</abstract>
    <identifier type="citekey">gonen-etal-2020-greek</identifier>
    <identifier type="doi">10.18653/v1/2020.blackboxnlp-1.5</identifier>
    <location>
        <url>https://aclanthology.org/2020.blackboxnlp-1.5/</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>45</start>
            <end>56</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T It‘s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
%A Gonen, Hila
%A Ravfogel, Shauli
%A Elazar, Yanai
%A Goldberg, Yoav
%Y Alishahi, Afra
%Y Belinkov, Yonatan
%Y Chrupała, Grzegorz
%Y Hupkes, Dieuwke
%Y Pinter, Yuval
%Y Sajjad, Hassan
%S Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F gonen-etal-2020-greek
%X Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple methods that expose remarkable translation capabilities with no fine-tuning. The results suggest that most of this information is encoded in a non-linear way, while some of it can also be recovered with purely linear tools. As part of our analysis, we test the hypothesis that mBERT learns representations which contain both a language-encoding component and an abstract, cross-lingual component, and explicitly identify an empirical language-identity subspace within mBERT representations.
%R 10.18653/v1/2020.blackboxnlp-1.5
%U https://aclanthology.org/2020.blackboxnlp-1.5/
%U https://doi.org/10.18653/v1/2020.blackboxnlp-1.5
%P 45-56

Markdown (Informal)

[It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT](https://aclanthology.org/2020.blackboxnlp-1.5/) (Gonen et al., BlackboxNLP 2020)

• It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT (Gonen et al., BlackboxNLP 2020)

ACL

• Hila Gonen, Shauli Ravfogel, Yanai Elazar, and Yoav Goldberg. 2020. It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 45–56, Online. Association for Computational Linguistics.