@inproceedings{yang-etal-2025-calibrating,
title = "Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification",
author = "Yang, Weiyi and
Zhang, Richong and
Chen, Junfan and
Sheng, Jiawei",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.658/",
doi = "10.18653/v1/2025.emnlp-main.658",
pages = "13015--13028",
ISBN = "979-8-89176-332-6",
abstract = "Semi-supervised text classification (SSTC) aims to train text classification models with few labeled data and massive unlabeled data. Existing studies develop effective pseudo-labeling methods, but they can struggle with unlabeled data that have imbalanced classes mismatched with the labeled data, making the pseudo-labeling biased towards majority classes, resulting in catastrophic error propagation. We believe it is crucial to explicitly estimate the overall class distribution, and use it to calibrate pseudo-labeling to constrain majority classes. To this end, we formulate the pseudo-labeling as an optimal transport (OT) problem, which transports the unlabeled sample distribution to the class distribution. With a memory bank, we dynamically collect both the high-confidence pseudo-labeled data and true labeled data, thus deriving reliable (pseudo-) labels for class distribution estimation. Empirical results on 3 commonly used benchmarks demonstrate that our model is effective and outperforms previous state-of-the-art methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-calibrating">
<titleInfo>
<title>Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Semi-supervised text classification (SSTC) aims to train text classification models with few labeled data and massive unlabeled data. Existing studies develop effective pseudo-labeling methods, but they can struggle with unlabeled data that have imbalanced classes mismatched with the labeled data, making the pseudo-labeling biased towards majority classes, resulting in catastrophic error propagation. We believe it is crucial to explicitly estimate the overall class distribution, and use it to calibrate pseudo-labeling to constrain majority classes. To this end, we formulate the pseudo-labeling as an optimal transport (OT) problem, which transports the unlabeled sample distribution to the class distribution. With a memory bank, we dynamically collect both the high-confidence pseudo-labeled data and true labeled data, thus deriving reliable (pseudo-) labels for class distribution estimation. Empirical results on 3 commonly used benchmarks demonstrate that our model is effective and outperforms previous state-of-the-art methods.</abstract>
<identifier type="citekey">yang-etal-2025-calibrating</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.658</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.658/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13015</start>
<end>13028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification
%A Yang, Weiyi
%A Zhang, Richong
%A Chen, Junfan
%A Sheng, Jiawei
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F yang-etal-2025-calibrating
%X Semi-supervised text classification (SSTC) aims to train text classification models with few labeled data and massive unlabeled data. Existing studies develop effective pseudo-labeling methods, but they can struggle with unlabeled data that have imbalanced classes mismatched with the labeled data, making the pseudo-labeling biased towards majority classes, resulting in catastrophic error propagation. We believe it is crucial to explicitly estimate the overall class distribution, and use it to calibrate pseudo-labeling to constrain majority classes. To this end, we formulate the pseudo-labeling as an optimal transport (OT) problem, which transports the unlabeled sample distribution to the class distribution. With a memory bank, we dynamically collect both the high-confidence pseudo-labeled data and true labeled data, thus deriving reliable (pseudo-) labels for class distribution estimation. Empirical results on 3 commonly used benchmarks demonstrate that our model is effective and outperforms previous state-of-the-art methods.
%R 10.18653/v1/2025.emnlp-main.658
%U https://aclanthology.org/2025.emnlp-main.658/
%U https://doi.org/10.18653/v1/2025.emnlp-main.658
%P 13015-13028
Markdown (Informal)
[Calibrating Pseudo-Labeling with Class Distribution for Semi-supervised Text Classification](https://aclanthology.org/2025.emnlp-main.658/) (Yang et al., EMNLP 2025)
ACL