<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-sat">
    <titleInfo>
        <title>SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soujanya</namePart>
        <namePart type="family">Poria</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>Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a simple instance-adaptive self-training method (SAT) for semi-supervised text classification. SAT first generates two augmented views for each unlabeled data, and then trains a meta learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views. The weakly-augmented view is fed to the model to produce a pseudo-label and the strongly-augmented view is used to train the model to predict the same pseudo-label. We conducted extensive experiments and analyses on three text classification datasets and found that with varying sizes of labeled training data, SAT consistently shows competitive performance compared to existing semi-supervised learning methods.</abstract>
    <identifier type="citekey">chen-etal-2022-sat</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.456</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.456</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6141</start>
            <end>6146</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training
%A Chen, Hui
%A Han, Wei
%A Poria, Soujanya
%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 chen-etal-2022-sat
%X Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a simple instance-adaptive self-training method (SAT) for semi-supervised text classification. SAT first generates two augmented views for each unlabeled data, and then trains a meta learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views. The weakly-augmented view is fed to the model to produce a pseudo-label and the strongly-augmented view is used to train the model to predict the same pseudo-label. We conducted extensive experiments and analyses on three text classification datasets and found that with varying sizes of labeled training data, SAT consistently shows competitive performance compared to existing semi-supervised learning methods.
%R 10.18653/v1/2022.findings-emnlp.456
%U https://aclanthology.org/2022.findings-emnlp.456
%U https://doi.org/10.18653/v1/2022.findings-emnlp.456
%P 6141-6146

Markdown (Informal)

[SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training](https://aclanthology.org/2022.findings-emnlp.456) (Chen et al., Findings 2022)

• SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training (Chen et al., Findings 2022)

ACL

• Hui Chen, Wei Han, and Soujanya Poria. 2022. SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6141–6146, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.