<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nonomura-etal-2026-mitigating">
    <titleInfo>
        <title>Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kanade</namePart>
        <namePart type="family">Nonomura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keita</namePart>
        <namePart type="family">Fukushima</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Risa</namePart>
        <namePart type="family">Kondo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tomoyuki</namePart>
        <namePart type="family">Kajiwara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saif</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Mohammad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nedjma</namePart>
            <namePart type="family">Ousidhoum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-413-2</identifier>
    </relatedItem>
    <abstract>We disentangle multilingual sentence embeddings into language-dependent and language-agnostic components, leveraging the latter to improve cross-lingual similarity estimation. Previous studies on this approach have trained disentanglers by combining intra-component constraints, which either align or disalign language-dependent embeddings or language-agnostic embeddings, with inter-component constraints across both embeddings. However, when and how these constraints are effective remains unclear. Our experiments on sentence similarity estimation and machine translation quality estimation revealed that while intra-component constraints and the combination of both constraints are effective for encoder-based multilingual sentence embeddings, inter-component constraints are effective for decoder-based ones. Furthermore, our detailed analysis revealed distinct roles: intra-component constraints improve uniformity within the embedding space, while inter-component constraints enhance cross-lingual alignment between parallel sentences.</abstract>
    <identifier type="citekey">nonomura-etal-2026-mitigating</identifier>
    <location>
        <url>https://aclanthology.org/2026.starsem-conference.26/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>385</start>
            <end>394</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation
%A Nonomura, Kanade
%A Fukushima, Keita
%A Kondo, Risa
%A Kajiwara, Tomoyuki
%Y Mohammad, Saif M.
%Y Ousidhoum, Nedjma
%S Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-413-2
%F nonomura-etal-2026-mitigating
%X We disentangle multilingual sentence embeddings into language-dependent and language-agnostic components, leveraging the latter to improve cross-lingual similarity estimation. Previous studies on this approach have trained disentanglers by combining intra-component constraints, which either align or disalign language-dependent embeddings or language-agnostic embeddings, with inter-component constraints across both embeddings. However, when and how these constraints are effective remains unclear. Our experiments on sentence similarity estimation and machine translation quality estimation revealed that while intra-component constraints and the combination of both constraints are effective for encoder-based multilingual sentence embeddings, inter-component constraints are effective for decoder-based ones. Furthermore, our detailed analysis revealed distinct roles: intra-component constraints improve uniformity within the embedding space, while inter-component constraints enhance cross-lingual alignment between parallel sentences.
%U https://aclanthology.org/2026.starsem-conference.26/
%P 385-394

Markdown (Informal)

[Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation](https://aclanthology.org/2026.starsem-conference.26/) (Nonomura et al., *SEM 2026)

• Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation (Nonomura et al., *SEM 2026)

ACL

• Kanade Nonomura, Keita Fukushima, Risa Kondo, and Tomoyuki Kajiwara. 2026. Mitigating Language Bias in Multilingual Sentence Embeddings for Cross-Lingual Similarity Estimation. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 385–394, San Diego, California, United States. Association for Computational Linguistics.