<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2021-self-supervised">
    <titleInfo>
        <title>Self-supervised Regularization for Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Meng</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zechen</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengtao</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL (Devlin et al., 2019a) is an unsupervised learning approach that defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human- provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg.</abstract>
    <identifier type="citekey">zhou-etal-2021-self-supervised</identifier>
    <identifier type="doi">10.1162/tacl_a_00389</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.39</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>641</start>
            <end>656</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Self-supervised Regularization for Text Classification
%A Zhou, Meng
%A Li, Zechen
%A Xie, Pengtao
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F zhou-etal-2021-self-supervised
%X Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL (Devlin et al., 2019a) is an unsupervised learning approach that defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human- provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg.
%R 10.1162/tacl_a_00389
%U https://aclanthology.org/2021.tacl-1.39
%U https://doi.org/10.1162/tacl_a_00389
%P 641-656

Markdown (Informal)

[Self-supervised Regularization for Text Classification](https://aclanthology.org/2021.tacl-1.39) (Zhou et al., TACL 2021)

• Self-supervised Regularization for Text Classification (Zhou et al., TACL 2021)

ACL

• Meng Zhou, Zechen Li, and Pengtao Xie. 2021. Self-supervised Regularization for Text Classification. Transactions of the Association for Computational Linguistics, 9:641–656.