@inproceedings{zou-caragea-2023-jointmatch,
title = "{J}oint{M}atch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification",
author = "Zou, Henry and
Caragea, Cornelia",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.451",
doi = "10.18653/v1/2023.emnlp-main.451",
pages = "7290--7301",
abstract = "Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. However, existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error accumulation. In this paper, we propose JointMatch, a holistic approach for SSTC that addresses these challenges by unifying ideas from recent semi-supervised learning and the task of learning with noise. JointMatch adaptively adjusts classwise thresholds based on the learning status of different classes to mitigate model bias towards current easy classes. Additionally, JointMatch alleviates error accumulation by utilizing two differently initialized networks to teach each other in a cross-labeling manner. To maintain divergence between the two networks for mutual learning, we introduce a strategy that weighs more disagreement data while also allowing the utilization of high-quality agreement data for training. Experimental results on benchmark datasets demonstrate the superior performance of JointMatch, achieving a significant 5.13{\%} improvement on average. Notably, JointMatch delivers impressive results even in the extremely-scarce-label setting, obtaining 86{\%} accuracy on AG News with only 5 labels per class. We make our code available at https://github.com/HenryPengZou/JointMatch.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-caragea-2023-jointmatch">
<titleInfo>
<title>JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. However, existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error accumulation. In this paper, we propose JointMatch, a holistic approach for SSTC that addresses these challenges by unifying ideas from recent semi-supervised learning and the task of learning with noise. JointMatch adaptively adjusts classwise thresholds based on the learning status of different classes to mitigate model bias towards current easy classes. Additionally, JointMatch alleviates error accumulation by utilizing two differently initialized networks to teach each other in a cross-labeling manner. To maintain divergence between the two networks for mutual learning, we introduce a strategy that weighs more disagreement data while also allowing the utilization of high-quality agreement data for training. Experimental results on benchmark datasets demonstrate the superior performance of JointMatch, achieving a significant 5.13% improvement on average. Notably, JointMatch delivers impressive results even in the extremely-scarce-label setting, obtaining 86% accuracy on AG News with only 5 labels per class. We make our code available at https://github.com/HenryPengZou/JointMatch.</abstract>
<identifier type="citekey">zou-caragea-2023-jointmatch</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.451</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.451</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7290</start>
<end>7301</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification
%A Zou, Henry
%A Caragea, Cornelia
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zou-caragea-2023-jointmatch
%X Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. However, existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error accumulation. In this paper, we propose JointMatch, a holistic approach for SSTC that addresses these challenges by unifying ideas from recent semi-supervised learning and the task of learning with noise. JointMatch adaptively adjusts classwise thresholds based on the learning status of different classes to mitigate model bias towards current easy classes. Additionally, JointMatch alleviates error accumulation by utilizing two differently initialized networks to teach each other in a cross-labeling manner. To maintain divergence between the two networks for mutual learning, we introduce a strategy that weighs more disagreement data while also allowing the utilization of high-quality agreement data for training. Experimental results on benchmark datasets demonstrate the superior performance of JointMatch, achieving a significant 5.13% improvement on average. Notably, JointMatch delivers impressive results even in the extremely-scarce-label setting, obtaining 86% accuracy on AG News with only 5 labels per class. We make our code available at https://github.com/HenryPengZou/JointMatch.
%R 10.18653/v1/2023.emnlp-main.451
%U https://aclanthology.org/2023.emnlp-main.451
%U https://doi.org/10.18653/v1/2023.emnlp-main.451
%P 7290-7301
Markdown (Informal)
[JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification](https://aclanthology.org/2023.emnlp-main.451) (Zou & Caragea, EMNLP 2023)
ACL