<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-english">
    <titleInfo>
        <title>English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yaushian</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ashley</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this work, we propose mSimCSE, which extends SimCSE to multilingual settings and reveal that contrastive learning on English data can surprisingly learn high-quality universal cross-lingual sentence embeddings without any parallel data.In unsupervised and weakly supervised settings, mSimCSE significantly improves previous sentence embedding methods on cross-lingual retrieval and multilingual STS tasks. The performance of unsupervised mSimCSE is comparable to fully supervised methods in retrieving low-resource languages and multilingual STS.The performance can be further enhanced when cross-lingual NLI data is available.</abstract>
    <identifier type="citekey">wang-etal-2022-english</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.621</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.621</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>9122</start>
            <end>9133</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
%A Wang, Yaushian
%A Wu, Ashley
%A Neubig, Graham
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-etal-2022-english
%X Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this work, we propose mSimCSE, which extends SimCSE to multilingual settings and reveal that contrastive learning on English data can surprisingly learn high-quality universal cross-lingual sentence embeddings without any parallel data.In unsupervised and weakly supervised settings, mSimCSE significantly improves previous sentence embedding methods on cross-lingual retrieval and multilingual STS tasks. The performance of unsupervised mSimCSE is comparable to fully supervised methods in retrieving low-resource languages and multilingual STS.The performance can be further enhanced when cross-lingual NLI data is available.
%R 10.18653/v1/2022.emnlp-main.621
%U https://aclanthology.org/2022.emnlp-main.621
%U https://doi.org/10.18653/v1/2022.emnlp-main.621
%P 9122-9133

Markdown (Informal)

[English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings](https://aclanthology.org/2022.emnlp-main.621) (Wang et al., EMNLP 2022)

• English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings (Wang et al., EMNLP 2022)

ACL

• Yaushian Wang, Ashley Wu, and Graham Neubig. 2022. English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9122–9133, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.