<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2019-generating-fluent">
    <titleInfo>
        <title>Generating Fluent Adversarial Examples for Natural Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Huangzhao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ning</namePart>
        <namePart type="family">Miao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lei</namePart>
        <namePart type="family">Li</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>Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHAoutperforms the baseline model on attacking capability. Adversarial training with MHA also leads to better robustness and performance.</abstract>
    <identifier type="citekey">zhang-etal-2019-generating-fluent</identifier>
    <identifier type="doi">10.18653/v1/P19-1559</identifier>
    <location>
        <url>https://aclanthology.org/P19-1559</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>5564</start>
            <end>5569</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generating Fluent Adversarial Examples for Natural Languages
%A Zhang, Huangzhao
%A Zhou, Hao
%A Miao, Ning
%A Li, Lei
%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-generating-fluent
%X Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHAoutperforms the baseline model on attacking capability. Adversarial training with MHA also leads to better robustness and performance.
%R 10.18653/v1/P19-1559
%U https://aclanthology.org/P19-1559
%U https://doi.org/10.18653/v1/P19-1559
%P 5564-5569

Markdown (Informal)

[Generating Fluent Adversarial Examples for Natural Languages](https://aclanthology.org/P19-1559) (Zhang et al., ACL 2019)

• Generating Fluent Adversarial Examples for Natural Languages (Zhang et al., ACL 2019)

ACL

• Huangzhao Zhang, Hao Zhou, Ning Miao, and Lei Li. 2019. Generating Fluent Adversarial Examples for Natural Languages. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5564–5569, Florence, Italy. Association for Computational Linguistics.