<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papadimitriou-etal-2023-multilingual">
    <titleInfo>
        <title>Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Isabel</namePart>
        <namePart type="family">Papadimitriou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kezia</namePart>
        <namePart type="family">Lopez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Jurafsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While multilingual language models can improve NLP performance on low-resource languages by leveraging higher-resource languages, they also reduce average performance on all languages (the ‘curse of multilinguality’). Here we show another problem with multilingual models: grammatical structures in higher-resource languages bleed into lower-resource languages, a phenomenon we call grammatical structure bias. We show this bias via a novel method for comparing the fluency of multilingual models to the fluency of monolingual Spanish and Greek models: testing their preference for two carefully-chosen variable grammatical structures (optional pronoun-drop in Spanish and optional Subject-Verb ordering in Greek). We find that multilingual BERT is biased toward the English-like setting (explicit pronouns and Subject-Verb-Object ordering) as compared to our monolingual control language model. With our case studies, we hope to bring to light the fine-grained ways in which multilingual models can be biased, and encourage more linguistically-aware fluency evaluation.</abstract>
    <identifier type="citekey">papadimitriou-etal-2023-multilingual</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.89</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.89/</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1194</start>
            <end>1200</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models
%A Papadimitriou, Isabel
%A Lopez, Kezia
%A Jurafsky, Dan
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F papadimitriou-etal-2023-multilingual
%X While multilingual language models can improve NLP performance on low-resource languages by leveraging higher-resource languages, they also reduce average performance on all languages (the ‘curse of multilinguality’). Here we show another problem with multilingual models: grammatical structures in higher-resource languages bleed into lower-resource languages, a phenomenon we call grammatical structure bias. We show this bias via a novel method for comparing the fluency of multilingual models to the fluency of monolingual Spanish and Greek models: testing their preference for two carefully-chosen variable grammatical structures (optional pronoun-drop in Spanish and optional Subject-Verb ordering in Greek). We find that multilingual BERT is biased toward the English-like setting (explicit pronouns and Subject-Verb-Object ordering) as compared to our monolingual control language model. With our case studies, we hope to bring to light the fine-grained ways in which multilingual models can be biased, and encourage more linguistically-aware fluency evaluation.
%R 10.18653/v1/2023.findings-eacl.89
%U https://aclanthology.org/2023.findings-eacl.89/
%U https://doi.org/10.18653/v1/2023.findings-eacl.89
%P 1194-1200

Markdown (Informal)

[Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models](https://aclanthology.org/2023.findings-eacl.89/) (Papadimitriou et al., Findings 2023)

• Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models (Papadimitriou et al., Findings 2023)

ACL

• Isabel Papadimitriou, Kezia Lopez, and Dan Jurafsky. 2023. Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1194–1200, Dubrovnik, Croatia. Association for Computational Linguistics.