<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-2024-covoswitch">
    <titleInfo>
        <title>CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yeeun</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Xiyan</namePart>
            <namePart type="family">Fu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Eve</namePart>
            <namePart type="family">Fleisig</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual code-switching research is often hindered by the lack and linguistically biased status of available datasets. To expand language representation, we synthesize code-switching data by replacing intonation units detected through PSST, a speech segmentation model fine-tuned from OpenAI’s Whisper, using a speech-to-text translation dataset, CoVoST 2. With our dataset, CoVoSwitch, spanning 13 languages, we evaluate the code-switching translation performance of two multilingual translation models, M2M-100 418M and NLLB-200 600M. We reveal that the inclusion of code-switching units results in higher translation performance than monolingual settings and that models are better at code-switching translation into English than non-English. Further, low-resource languages gain most from integration of code-switched units when translating into English but much less when translating into non-English. Translations into low-resource languages also perform worse than even raw code-switched inputs. We find that systems excel at copying English tokens but struggle with non-English tokens, that the off-target problem in monolingual settings is also relevant in code-switching settings, and that models hallucinate in code-switching translation by introducing words absent in both of the original source sentences. CoVoSwitch and code are available at https://github.com/sophiayk20/covoswitch.</abstract>
    <identifier type="citekey">kang-2024-covoswitch</identifier>
    <identifier type="doi">10.18653/v1/2024.acl-srw.40</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-srw.40</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>345</start>
            <end>357</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units
%A Kang, Yeeun
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kang-2024-covoswitch
%X Multilingual code-switching research is often hindered by the lack and linguistically biased status of available datasets. To expand language representation, we synthesize code-switching data by replacing intonation units detected through PSST, a speech segmentation model fine-tuned from OpenAI’s Whisper, using a speech-to-text translation dataset, CoVoST 2. With our dataset, CoVoSwitch, spanning 13 languages, we evaluate the code-switching translation performance of two multilingual translation models, M2M-100 418M and NLLB-200 600M. We reveal that the inclusion of code-switching units results in higher translation performance than monolingual settings and that models are better at code-switching translation into English than non-English. Further, low-resource languages gain most from integration of code-switched units when translating into English but much less when translating into non-English. Translations into low-resource languages also perform worse than even raw code-switched inputs. We find that systems excel at copying English tokens but struggle with non-English tokens, that the off-target problem in monolingual settings is also relevant in code-switching settings, and that models hallucinate in code-switching translation by introducing words absent in both of the original source sentences. CoVoSwitch and code are available at https://github.com/sophiayk20/covoswitch.
%R 10.18653/v1/2024.acl-srw.40
%U https://aclanthology.org/2024.acl-srw.40
%U https://doi.org/10.18653/v1/2024.acl-srw.40
%P 345-357

Markdown (Informal)

[CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units](https://aclanthology.org/2024.acl-srw.40) (Kang, ACL 2024)

• CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units (Kang, ACL 2024)

ACL

• Yeeun Kang. 2024. CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 345–357, Bangkok, Thailand. Association for Computational Linguistics.