<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2021-adversarial-examples">
    <titleInfo>
        <title>Adversarial Examples for Evaluating Math Word Problem Solvers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rishabh</namePart>
        <namePart type="family">Maheshwary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vikram</namePart>
        <namePart type="family">Pudi</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>Findings of the Association for Computational Linguistics: EMNLP 2021</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">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets. However, the extent to which existing MWP solvers truly understand language and its relation with numbers is still unclear. In this paper, we generate adversarial attacks to evaluate the robustness of state-of-the-art MWP solvers. We propose two methods, Question Reordering and Sentence Paraphrasing to generate adversarial attacks. We conduct experiments across three neural MWP solvers over two benchmark datasets. On average, our attack method is able to reduce the accuracy of MWP solvers by over 40% on these datasets. Our results demonstrate that existing MWP solvers are sensitive to linguistic variations in the problem text. We verify the validity and quality of generated adversarial examples through human evaluation.</abstract>
    <identifier type="citekey">kumar-etal-2021-adversarial-examples</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.230</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.230/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>2705</start>
            <end>2712</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adversarial Examples for Evaluating Math Word Problem Solvers
%A Kumar, Vivek
%A Maheshwary, Rishabh
%A Pudi, Vikram
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F kumar-etal-2021-adversarial-examples
%X Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets. However, the extent to which existing MWP solvers truly understand language and its relation with numbers is still unclear. In this paper, we generate adversarial attacks to evaluate the robustness of state-of-the-art MWP solvers. We propose two methods, Question Reordering and Sentence Paraphrasing to generate adversarial attacks. We conduct experiments across three neural MWP solvers over two benchmark datasets. On average, our attack method is able to reduce the accuracy of MWP solvers by over 40% on these datasets. Our results demonstrate that existing MWP solvers are sensitive to linguistic variations in the problem text. We verify the validity and quality of generated adversarial examples through human evaluation.
%R 10.18653/v1/2021.findings-emnlp.230
%U https://aclanthology.org/2021.findings-emnlp.230/
%U https://doi.org/10.18653/v1/2021.findings-emnlp.230
%P 2705-2712

Markdown (Informal)

[Adversarial Examples for Evaluating Math Word Problem Solvers](https://aclanthology.org/2021.findings-emnlp.230/) (Kumar et al., Findings 2021)

• Adversarial Examples for Evaluating Math Word Problem Solvers (Kumar et al., Findings 2021)

ACL

• Vivek Kumar, Rishabh Maheshwary, and Vikram Pudi. 2021. Adversarial Examples for Evaluating Math Word Problem Solvers. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2705–2712, Punta Cana, Dominican Republic. Association for Computational Linguistics.