<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonen-etal-2022-analyzing">
    <titleInfo>
        <title>Analyzing Gender Representation in Multilingual Models</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">Yoav</namePart>
        <namePart type="family">Goldberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 7th Workshop on Representation Learning for NLP</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representations of gender distinctions as a practical case study, and examine the extent to which the gender concept is encoded in shared subspaces across different languages. Our analysis shows that gender representations consist of several prominent components that are shared across languages, alongside language-specific components. The existence of language-independent and language-specific components provides an explanation for an intriguing empirical observation we make”:” while gender classification transfers well across languages, interventions for gender removal trained on a single language do not transfer easily to others.</abstract>
    <identifier type="citekey">gonen-etal-2022-analyzing</identifier>
    <identifier type="doi">10.18653/v1/2022.repl4nlp-1.8</identifier>
    <location>
        <url>https://aclanthology.org/2022.repl4nlp-1.8</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>67</start>
            <end>77</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Analyzing Gender Representation in Multilingual Models
%A Gonen, Hila
%A Ravfogel, Shauli
%A Goldberg, Yoav
%S Proceedings of the 7th Workshop on Representation Learning for NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F gonen-etal-2022-analyzing
%X Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representations of gender distinctions as a practical case study, and examine the extent to which the gender concept is encoded in shared subspaces across different languages. Our analysis shows that gender representations consist of several prominent components that are shared across languages, alongside language-specific components. The existence of language-independent and language-specific components provides an explanation for an intriguing empirical observation we make”:” while gender classification transfers well across languages, interventions for gender removal trained on a single language do not transfer easily to others.
%R 10.18653/v1/2022.repl4nlp-1.8
%U https://aclanthology.org/2022.repl4nlp-1.8
%U https://doi.org/10.18653/v1/2022.repl4nlp-1.8
%P 67-77

Markdown (Informal)

[Analyzing Gender Representation in Multilingual Models](https://aclanthology.org/2022.repl4nlp-1.8) (Gonen et al., RepL4NLP 2022)

• Analyzing Gender Representation in Multilingual Models (Gonen et al., RepL4NLP 2022)

ACL

• Hila Gonen, Shauli Ravfogel, and Yoav Goldberg. 2022. Analyzing Gender Representation in Multilingual Models. In Proceedings of the 7th Workshop on Representation Learning for NLP, pages 67–77, Dublin, Ireland. Association for Computational Linguistics.