<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2019-bridging">
    <titleInfo>
        <title>Bridging the Gap between Training and Inference for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fandong</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">You</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qun</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese-\textgreaterEnglish and WMT’14 English-\textgreaterGerman translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.</abstract>
    <identifier type="citekey">zhang-etal-2019-bridging</identifier>
    <identifier type="doi">10.18653/v1/P19-1426</identifier>
    <location>
        <url>https://aclanthology.org/P19-1426</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>4334</start>
            <end>4343</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Bridging the Gap between Training and Inference for Neural Machine Translation
%A Zhang, Wen
%A Feng, Yang
%A Meng, Fandong
%A You, Di
%A Liu, Qun
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F zhang-etal-2019-bridging
%X Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese-\textgreaterEnglish and WMT’14 English-\textgreaterGerman translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.
%R 10.18653/v1/P19-1426
%U https://aclanthology.org/P19-1426
%U https://doi.org/10.18653/v1/P19-1426
%P 4334-4343

Markdown (Informal)

[Bridging the Gap between Training and Inference for Neural Machine Translation](https://aclanthology.org/P19-1426) (Zhang et al., ACL 2019)

• Bridging the Gap between Training and Inference for Neural Machine Translation (Zhang et al., ACL 2019)

ACL

• Wen Zhang, Yang Feng, Fandong Meng, Di You, and Qun Liu. 2019. Bridging the Gap between Training and Inference for Neural Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4334–4343, Florence, Italy. Association for Computational Linguistics.