<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imamura-etal-2023-pivot">
    <titleInfo>
        <title>Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kenji</namePart>
        <namePart type="family">Imamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masao</namePart>
        <namePart type="family">Utiyama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eiichiro</namePart>
        <namePart type="family">Sumita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Masao</namePart>
            <namePart type="family">Utiyama</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Asia-Pacific Association for Machine Translation</publisher>
            <place>
                <placeTerm type="text">Macau SAR, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A multilingual translation model enables a single model to handle multiple languages. However, the translation qualities of unlearned language pairs (i.e., zero-shot translation qualities) are still poor. By contrast, pivot translation translates source texts into target ones via a pivot language such as English, thus enabling machine translation without parallel texts between the source and target languages. In this paper, we perform pivot translation using a multilingual model and compare it with direct translation. We improve the translation quality without using parallel texts of direct translation by fine-tuning the model with machine-translated pseudo-translations. We also discuss what type of parallel texts are suitable for effectively improving the translation quality in multilingual pivot translation.</abstract>
    <identifier type="citekey">imamura-etal-2023-pivot</identifier>
    <location>
        <url>https://aclanthology.org/2023.mtsummit-research.29</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>348</start>
            <end>359</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model
%A Imamura, Kenji
%A Utiyama, Masao
%A Sumita, Eiichiro
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F imamura-etal-2023-pivot
%X A multilingual translation model enables a single model to handle multiple languages. However, the translation qualities of unlearned language pairs (i.e., zero-shot translation qualities) are still poor. By contrast, pivot translation translates source texts into target ones via a pivot language such as English, thus enabling machine translation without parallel texts between the source and target languages. In this paper, we perform pivot translation using a multilingual model and compare it with direct translation. We improve the translation quality without using parallel texts of direct translation by fine-tuning the model with machine-translated pseudo-translations. We also discuss what type of parallel texts are suitable for effectively improving the translation quality in multilingual pivot translation.
%U https://aclanthology.org/2023.mtsummit-research.29
%P 348-359

Markdown (Informal)

[Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model](https://aclanthology.org/2023.mtsummit-research.29) (Imamura et al., MTSummit 2023)

• Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model (Imamura et al., MTSummit 2023)

ACL

• Kenji Imamura, Masao Utiyama, and Eiichiro Sumita. 2023. Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 348–359, Macau SAR, China. Asia-Pacific Association for Machine Translation.