<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brimacombe-zhou-2023-quick">
    <titleInfo>
        <title>Quick Back-Translation for Unsupervised Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Brimacombe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiawei</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The field of unsupervised machine translation has seen significant advancement from the marriage of the Transformer and the back-translation algorithm. The Transformer is a powerful generative model, and back-translation leverages Transformer’s high-quality translations for iterative self-improvement. However, the Transformer is encumbered by the run-time of autoregressive inference during back-translation, and back-translation is limited by a lack of synthetic data efficiency. We propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). QBT re-purposes the encoder as a generative model, and uses encoder-generated sequences to train the decoder in conjunction with the original autoregressive back-translation step, improving data throughput and utilization. Experiments on various WMT benchmarks demonstrate that a relatively small number of refining steps of QBT improve current unsupervised machine translation models, and that QBT dramatically outperforms standard back-translation only method in terms of training efficiency for comparable translation qualities.</abstract>
    <identifier type="citekey">brimacombe-zhou-2023-quick</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.571</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.571</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>8521</start>
            <end>8534</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Quick Back-Translation for Unsupervised Machine Translation
%A Brimacombe, Benjamin
%A Zhou, Jiawei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F brimacombe-zhou-2023-quick
%X The field of unsupervised machine translation has seen significant advancement from the marriage of the Transformer and the back-translation algorithm. The Transformer is a powerful generative model, and back-translation leverages Transformer’s high-quality translations for iterative self-improvement. However, the Transformer is encumbered by the run-time of autoregressive inference during back-translation, and back-translation is limited by a lack of synthetic data efficiency. We propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). QBT re-purposes the encoder as a generative model, and uses encoder-generated sequences to train the decoder in conjunction with the original autoregressive back-translation step, improving data throughput and utilization. Experiments on various WMT benchmarks demonstrate that a relatively small number of refining steps of QBT improve current unsupervised machine translation models, and that QBT dramatically outperforms standard back-translation only method in terms of training efficiency for comparable translation qualities.
%R 10.18653/v1/2023.findings-emnlp.571
%U https://aclanthology.org/2023.findings-emnlp.571
%U https://doi.org/10.18653/v1/2023.findings-emnlp.571
%P 8521-8534

Markdown (Informal)

[Quick Back-Translation for Unsupervised Machine Translation](https://aclanthology.org/2023.findings-emnlp.571) (Brimacombe & Zhou, Findings 2023)

• Quick Back-Translation for Unsupervised Machine Translation (Brimacombe & Zhou, Findings 2023)

ACL

• Benjamin Brimacombe and Jiawei Zhou. 2023. Quick Back-Translation for Unsupervised Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8521–8534, Singapore. Association for Computational Linguistics.