<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-etal-2022-synergy">
    <titleInfo>
        <title>Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jaehoon</namePart>
        <namePart type="family">Oh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jongwoo</namePart>
        <namePart type="family">Ko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Se-Young</namePart>
        <namePart type="family">Yun</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>Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to generate the source language data from the target language data for inference. However, prior works have not considered the use of both translations simultaneously. This paper shows that combining them can synergize the results on various multilingual sentence classification tasks. We empirically find that translation artifacts stylized by translators are the main factor of the performance gain. Based on this analysis, we adopt two training methods, SupCon and MixUp, considering translation artifacts. Furthermore, we propose a cross-lingual fine-tuning algorithm called MUSC, which uses SupCon and MixUp jointly and improves the performance. Our code is available at https://github.com/jongwooko/MUSC.</abstract>
    <identifier type="citekey">oh-etal-2022-synergy</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.452</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.452</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6747</start>
            <end>6754</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
%A Oh, Jaehoon
%A Ko, Jongwoo
%A Yun, Se-Young
%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 oh-etal-2022-synergy
%X Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to generate the source language data from the target language data for inference. However, prior works have not considered the use of both translations simultaneously. This paper shows that combining them can synergize the results on various multilingual sentence classification tasks. We empirically find that translation artifacts stylized by translators are the main factor of the performance gain. Based on this analysis, we adopt two training methods, SupCon and MixUp, considering translation artifacts. Furthermore, we propose a cross-lingual fine-tuning algorithm called MUSC, which uses SupCon and MixUp jointly and improves the performance. Our code is available at https://github.com/jongwooko/MUSC.
%R 10.18653/v1/2022.emnlp-main.452
%U https://aclanthology.org/2022.emnlp-main.452
%U https://doi.org/10.18653/v1/2022.emnlp-main.452
%P 6747-6754

Markdown (Informal)

[Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks](https://aclanthology.org/2022.emnlp-main.452) (Oh et al., EMNLP 2022)

• Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks (Oh et al., EMNLP 2022)

ACL

• Jaehoon Oh, Jongwoo Ko, and Se-Young Yun. 2022. Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6747–6754, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.