@inproceedings{piedboeuf-langlais-2025-evaluation,
title = "On Evaluation Protocols for Data Augmentation in a Limited Data Scenario",
author = "Piedboeuf, Fr{\'e}d{\'e}ric and
Langlais, Philippe",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.231/",
pages = "3428--3443",
abstract = "Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed, and that has demonstrated great efficiency on small data settings, at least for text classification tasks. In this paper, we challenge those results, showing that classical data augmentation (which modify sentences) is simply a way of performing better fine-tuning, and that spending more time doing so before applying data augmentation negates its effect. This is a significant contribution as it answers several questions that were left open in recent years, namely : which DA technique performs best (all of them as long as they generate data close enough to the training set, as to not impair training) and why did DA show positive results (facilitates training of network). We further show that zero- and few-shot DA via conversational agents such as ChatGPT or LLama2 can increase performances, confirming that this form of data augmentation is preferable to classical methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="piedboeuf-langlais-2025-evaluation">
<titleInfo>
<title>On Evaluation Protocols for Data Augmentation in a Limited Data Scenario</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Piedboeuf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed, and that has demonstrated great efficiency on small data settings, at least for text classification tasks. In this paper, we challenge those results, showing that classical data augmentation (which modify sentences) is simply a way of performing better fine-tuning, and that spending more time doing so before applying data augmentation negates its effect. This is a significant contribution as it answers several questions that were left open in recent years, namely : which DA technique performs best (all of them as long as they generate data close enough to the training set, as to not impair training) and why did DA show positive results (facilitates training of network). We further show that zero- and few-shot DA via conversational agents such as ChatGPT or LLama2 can increase performances, confirming that this form of data augmentation is preferable to classical methods.</abstract>
<identifier type="citekey">piedboeuf-langlais-2025-evaluation</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.231/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3428</start>
<end>3443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Evaluation Protocols for Data Augmentation in a Limited Data Scenario
%A Piedboeuf, Frédéric
%A Langlais, Philippe
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F piedboeuf-langlais-2025-evaluation
%X Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed, and that has demonstrated great efficiency on small data settings, at least for text classification tasks. In this paper, we challenge those results, showing that classical data augmentation (which modify sentences) is simply a way of performing better fine-tuning, and that spending more time doing so before applying data augmentation negates its effect. This is a significant contribution as it answers several questions that were left open in recent years, namely : which DA technique performs best (all of them as long as they generate data close enough to the training set, as to not impair training) and why did DA show positive results (facilitates training of network). We further show that zero- and few-shot DA via conversational agents such as ChatGPT or LLama2 can increase performances, confirming that this form of data augmentation is preferable to classical methods.
%U https://aclanthology.org/2025.coling-main.231/
%P 3428-3443
Markdown (Informal)
[On Evaluation Protocols for Data Augmentation in a Limited Data Scenario](https://aclanthology.org/2025.coling-main.231/) (Piedboeuf & Langlais, COLING 2025)
ACL