<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hai-etal-2022-learning">
    <titleInfo>
        <title>Learning Invariant Representation Improves Robustness for MRC Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Hai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoran</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianyu</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Houfeng</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The prosperity of Pretrained Language Models(PLM) has greatly promoted the development of Machine Reading Comprehension (MRC). However, these models are vulnerable and not robust to adversarial examples. In this paper, we propose Stable and Contrastive Question Answering (SCQA) to improve invariance of representation to alleviate these robustness issues. Specifically, we first construct positive example pairs which have same answer through data augmentation. Then SCQA learns enhanced representations with better alignment between positive pairs by introducing stability and contrastive loss. Experimental results show that our approach can boost the robustness of QA models cross different MRC tasks and attack sets significantly and consistently.</abstract>
    <identifier type="citekey">hai-etal-2022-learning</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.241</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.241/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>3306</start>
            <end>3314</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Invariant Representation Improves Robustness for MRC Models
%A Hai, Yu
%A Wen, Liang
%A Meng, Haoran
%A Liu, Tianyu
%A Wang, Houfeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hai-etal-2022-learning
%X The prosperity of Pretrained Language Models(PLM) has greatly promoted the development of Machine Reading Comprehension (MRC). However, these models are vulnerable and not robust to adversarial examples. In this paper, we propose Stable and Contrastive Question Answering (SCQA) to improve invariance of representation to alleviate these robustness issues. Specifically, we first construct positive example pairs which have same answer through data augmentation. Then SCQA learns enhanced representations with better alignment between positive pairs by introducing stability and contrastive loss. Experimental results show that our approach can boost the robustness of QA models cross different MRC tasks and attack sets significantly and consistently.
%R 10.18653/v1/2022.findings-emnlp.241
%U https://aclanthology.org/2022.findings-emnlp.241/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.241
%P 3306-3314

Markdown (Informal)

[Learning Invariant Representation Improves Robustness for MRC Models](https://aclanthology.org/2022.findings-emnlp.241/) (Hai et al., Findings 2022)

• Learning Invariant Representation Improves Robustness for MRC Models (Hai et al., Findings 2022)

ACL

• Yu Hai, Liang Wen, Haoran Meng, Tianyu Liu, and Houfeng Wang. 2022. Learning Invariant Representation Improves Robustness for MRC Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3306–3314, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.