<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2021-improving">
    <titleInfo>
        <title>Improving Neural Machine Translation by Bidirectional Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dacheng</namePart>
        <namePart type="family">Tao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a simple and effective pretraining strategy – bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from “src\rightarrowtgt” to “src+tgt\rightarrowtgt+src” without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs (data sizes range from 160K to 38M) significantly higher. Encouragingly, our proposed model can complement existing data manipulation strategies, i.e. back translation, data distillation, and data diversification. Extensive analyses show that our approach functions as a novel bilingual code-switcher, obtaining better bilingual alignment.</abstract>
    <identifier type="citekey">ding-etal-2021-improving</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.263</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.263/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>3278</start>
            <end>3284</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Neural Machine Translation by Bidirectional Training
%A Ding, Liang
%A Wu, Di
%A Tao, Dacheng
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F ding-etal-2021-improving
%X We present a simple and effective pretraining strategy – bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from “src\rightarrowtgt” to “src+tgt\rightarrowtgt+src” without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs (data sizes range from 160K to 38M) significantly higher. Encouragingly, our proposed model can complement existing data manipulation strategies, i.e. back translation, data distillation, and data diversification. Extensive analyses show that our approach functions as a novel bilingual code-switcher, obtaining better bilingual alignment.
%R 10.18653/v1/2021.emnlp-main.263
%U https://aclanthology.org/2021.emnlp-main.263/
%U https://doi.org/10.18653/v1/2021.emnlp-main.263
%P 3278-3284

Markdown (Informal)

[Improving Neural Machine Translation by Bidirectional Training](https://aclanthology.org/2021.emnlp-main.263/) (Ding et al., EMNLP 2021)

• Improving Neural Machine Translation by Bidirectional Training (Ding et al., EMNLP 2021)

ACL

• Liang Ding, Di Wu, and Dacheng Tao. 2021. Improving Neural Machine Translation by Bidirectional Training. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3278–3284, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.