<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-lam-2021-towards">
    <titleInfo>
        <title>Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wai</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Held Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we investigate the Domain Generalization (DG) problem for supervised Paraphrase Identification (PI). We observe that the performance of existing PI models deteriorates dramatically when tested in an out-of-distribution (OOD) domain. We conjecture that it is caused by shortcut learning, i.e., these models tend to utilize the cue words that are unique for a particular dataset or domain. To alleviate this issue and enhance the DG ability, we propose a PI framework based on Optimal Transport (OT). Our method forces the network to learn the necessary features for all the words in the input, which alleviates the shortcut learning problem. Experimental results show that our method improves the DG ability for the PI models.</abstract>
    <identifier type="citekey">shen-lam-2021-towards</identifier>
    <location>
        <url>https://aclanthology.org/2021.ranlp-1.148</url>
    </location>
    <part>
        <date>2021-09</date>
        <extent unit="page">
            <start>1318</start>
            <end>1325</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning
%A Shen, Xin
%A Lam, Wai
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F shen-lam-2021-towards
%X In this paper, we investigate the Domain Generalization (DG) problem for supervised Paraphrase Identification (PI). We observe that the performance of existing PI models deteriorates dramatically when tested in an out-of-distribution (OOD) domain. We conjecture that it is caused by shortcut learning, i.e., these models tend to utilize the cue words that are unique for a particular dataset or domain. To alleviate this issue and enhance the DG ability, we propose a PI framework based on Optimal Transport (OT). Our method forces the network to learn the necessary features for all the words in the input, which alleviates the shortcut learning problem. Experimental results show that our method improves the DG ability for the PI models.
%U https://aclanthology.org/2021.ranlp-1.148
%P 1318-1325

Markdown (Informal)

[Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning](https://aclanthology.org/2021.ranlp-1.148) (Shen & Lam, RANLP 2021)

• Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning (Shen & Lam, RANLP 2021)

ACL

• Xin Shen and Wai Lam. 2021. Towards Domain-Generalizable Paraphrase Identification by Avoiding the Shortcut Learning. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1318–1325, Held Online. INCOMA Ltd..