<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pruthi-etal-2019-combating">
    <titleInfo>
        <title>Combating Adversarial Misspellings with Robust Word Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Danish</namePart>
        <namePart type="family">Pruthi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bhuwan</namePart>
        <namePart type="family">Dhingra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zachary</namePart>
        <namePart type="given">C</namePart>
        <namePart type="family">Lipton</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>To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff strategies for handling rare and unseen words. Trained to recognize words corrupted by random adds, drops, swaps, and keyboard mistakes, our method achieves 32% relative (and 3.3% absolute) error reduction over the vanilla semi-character model. Notably, our pipeline confers robustness on the downstream classifier, outperforming both adversarial training and off-the-shelf spell checkers. Against a BERT model fine-tuned for sentiment analysis, a single adversarially-chosen character attack lowers accuracy from 90.3% to 45.8%. Our defense restores accuracy to 75%. Surprisingly, better word recognition does not always entail greater robustness. Our analysis reveals that robustness also depends upon a quantity that we denote the sensitivity.</abstract>
    <identifier type="citekey">pruthi-etal-2019-combating</identifier>
    <identifier type="doi">10.18653/v1/P19-1561</identifier>
    <location>
        <url>https://aclanthology.org/P19-1561</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>5582</start>
            <end>5591</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Combating Adversarial Misspellings with Robust Word Recognition
%A Pruthi, Danish
%A Dhingra, Bhuwan
%A Lipton, Zachary C.
%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 pruthi-etal-2019-combating
%X To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff strategies for handling rare and unseen words. Trained to recognize words corrupted by random adds, drops, swaps, and keyboard mistakes, our method achieves 32% relative (and 3.3% absolute) error reduction over the vanilla semi-character model. Notably, our pipeline confers robustness on the downstream classifier, outperforming both adversarial training and off-the-shelf spell checkers. Against a BERT model fine-tuned for sentiment analysis, a single adversarially-chosen character attack lowers accuracy from 90.3% to 45.8%. Our defense restores accuracy to 75%. Surprisingly, better word recognition does not always entail greater robustness. Our analysis reveals that robustness also depends upon a quantity that we denote the sensitivity.
%R 10.18653/v1/P19-1561
%U https://aclanthology.org/P19-1561
%U https://doi.org/10.18653/v1/P19-1561
%P 5582-5591

Markdown (Informal)

[Combating Adversarial Misspellings with Robust Word Recognition](https://aclanthology.org/P19-1561) (Pruthi et al., ACL 2019)

• Combating Adversarial Misspellings with Robust Word Recognition (Pruthi et al., ACL 2019)

ACL

• Danish Pruthi, Bhuwan Dhingra, and Zachary C. Lipton. 2019. Combating Adversarial Misspellings with Robust Word Recognition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5582–5591, Florence, Italy. Association for Computational Linguistics.