<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2019-robust">
    <titleInfo>
        <title>Robust Neural Machine Translation with Doubly Adversarial Inputs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yong</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lu</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wolfgang</namePart>
        <namePart type="family">Macherey</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) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to improve its robustness against the adversarial source inputs. For the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs. Experimental results on Chinese-English and English-German translation tasks demonstrate that our approach achieves significant improvements (2.8 and 1.6 BLEU points) over Transformer on standard clean benchmarks as well as exhibiting higher robustness on noisy data.</abstract>
    <identifier type="citekey">cheng-etal-2019-robust</identifier>
    <identifier type="doi">10.18653/v1/P19-1425</identifier>
    <location>
        <url>https://aclanthology.org/P19-1425</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>4324</start>
            <end>4333</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Robust Neural Machine Translation with Doubly Adversarial Inputs
%A Cheng, Yong
%A Jiang, Lu
%A Macherey, Wolfgang
%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 cheng-etal-2019-robust
%X Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to improve its robustness against the adversarial source inputs. For the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs. Experimental results on Chinese-English and English-German translation tasks demonstrate that our approach achieves significant improvements (2.8 and 1.6 BLEU points) over Transformer on standard clean benchmarks as well as exhibiting higher robustness on noisy data.
%R 10.18653/v1/P19-1425
%U https://aclanthology.org/P19-1425
%U https://doi.org/10.18653/v1/P19-1425
%P 4324-4333

Markdown (Informal)

[Robust Neural Machine Translation with Doubly Adversarial Inputs](https://aclanthology.org/P19-1425) (Cheng et al., ACL 2019)

• Robust Neural Machine Translation with Doubly Adversarial Inputs (Cheng et al., ACL 2019)

ACL

• Yong Cheng, Lu Jiang, and Wolfgang Macherey. 2019. Robust Neural Machine Translation with Doubly Adversarial Inputs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4324–4333, Florence, Italy. Association for Computational Linguistics.