@inproceedings{ding-etal-2026-self,
title = "Self-supervised Data Augmentation for Text Classification in Low-Data Settings",
author = "Ding, Deyu and
Wang, Mengying and
Spitz, Andreas",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.788/",
doi = "10.63317/2zryuih2ucnr",
pages = "10046--10056",
abstract = "Due to data sparsity and high annotation cost, data augmentation has established itself as an effective tool for boosting model performance on supervised NLP tasks. Where task-agnostic augmentation methods tend to act as simple regularizers for the data, task-aware methods also leverage labels for the generation of data that are most suitable for downstream tasks. While prior work has investigated generation and sampling strategies individually, the potential of a self-supervised approach that leverages multiple pre-trained models in generation and sampling remains underexplored. To address this issue, we present an ensemble-based framework of language models that proposes augmentation candidates and internally reviews their suitability for low-resource text classification tasks. We evaluate our model on six classification benchmarks and find that it consistently outperforms state-of-the-art data augmentation baselines in classification accuracy by an average of 0.97 points in low-data scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2026-self">
<titleInfo>
<title>Self-supervised Data Augmentation for Text Classification in Low-Data Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deyu</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Spitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to data sparsity and high annotation cost, data augmentation has established itself as an effective tool for boosting model performance on supervised NLP tasks. Where task-agnostic augmentation methods tend to act as simple regularizers for the data, task-aware methods also leverage labels for the generation of data that are most suitable for downstream tasks. While prior work has investigated generation and sampling strategies individually, the potential of a self-supervised approach that leverages multiple pre-trained models in generation and sampling remains underexplored. To address this issue, we present an ensemble-based framework of language models that proposes augmentation candidates and internally reviews their suitability for low-resource text classification tasks. We evaluate our model on six classification benchmarks and find that it consistently outperforms state-of-the-art data augmentation baselines in classification accuracy by an average of 0.97 points in low-data scenarios.</abstract>
<identifier type="citekey">ding-etal-2026-self</identifier>
<identifier type="doi">10.63317/2zryuih2ucnr</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.788/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10046</start>
<end>10056</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-supervised Data Augmentation for Text Classification in Low-Data Settings
%A Ding, Deyu
%A Wang, Mengying
%A Spitz, Andreas
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ding-etal-2026-self
%X Due to data sparsity and high annotation cost, data augmentation has established itself as an effective tool for boosting model performance on supervised NLP tasks. Where task-agnostic augmentation methods tend to act as simple regularizers for the data, task-aware methods also leverage labels for the generation of data that are most suitable for downstream tasks. While prior work has investigated generation and sampling strategies individually, the potential of a self-supervised approach that leverages multiple pre-trained models in generation and sampling remains underexplored. To address this issue, we present an ensemble-based framework of language models that proposes augmentation candidates and internally reviews their suitability for low-resource text classification tasks. We evaluate our model on six classification benchmarks and find that it consistently outperforms state-of-the-art data augmentation baselines in classification accuracy by an average of 0.97 points in low-data scenarios.
%R 10.63317/2zryuih2ucnr
%U https://aclanthology.org/2026.lrec-1.788/
%U https://doi.org/10.63317/2zryuih2ucnr
%P 10046-10056
Markdown (Informal)
[Self-supervised Data Augmentation for Text Classification in Low-Data Settings](https://aclanthology.org/2026.lrec-1.788/) (Ding et al., LREC 2026)
ACL