@inproceedings{gonzalez-gutierrez-etal-2024-fine,
title = "Does Fine-tuning a Classifier Help in Low-budget Scenarios? Not Much",
author = "Gonzalez - Gutierrez, Cesar and
Primadhanty, Audi and
Cazzaro, Francesco and
Quattoni, Ariadna",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fifth Workshop on Insights from Negative Results in NLP",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.insights-1.3",
doi = "10.18653/v1/2024.insights-1.3",
pages = "17--24",
abstract = "In recent years, the two-step approach for text classification based on pre-training plus fine-tuning has led to significant improvements in classification performance. In this paper, we study the low-budget scenario, and we ask whether it is justified to allocate the additional resources needed for fine-tuning complex models. To do so, we isolate the gains obtained from pre-training from those obtained from fine-tuning. We find out that, when the gains from pre-training are factored out, the performance attained by using complex transformer models leads to marginal improvements over simpler models. Therefore, in this scenario, utilizing simpler classifiers on top of pre-trained representations proves to be a viable alternative.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-gutierrez-etal-2024-fine">
<titleInfo>
<title>Does Fine-tuning a Classifier Help in Low-budget Scenarios? Not Much</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cesar</namePart>
<namePart type="family">Gonzalez - Gutierrez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Audi</namePart>
<namePart type="family">Primadhanty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Cazzaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariadna</namePart>
<namePart type="family">Quattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, the two-step approach for text classification based on pre-training plus fine-tuning has led to significant improvements in classification performance. In this paper, we study the low-budget scenario, and we ask whether it is justified to allocate the additional resources needed for fine-tuning complex models. To do so, we isolate the gains obtained from pre-training from those obtained from fine-tuning. We find out that, when the gains from pre-training are factored out, the performance attained by using complex transformer models leads to marginal improvements over simpler models. Therefore, in this scenario, utilizing simpler classifiers on top of pre-trained representations proves to be a viable alternative.</abstract>
<identifier type="citekey">gonzalez-gutierrez-etal-2024-fine</identifier>
<identifier type="doi">10.18653/v1/2024.insights-1.3</identifier>
<location>
<url>https://aclanthology.org/2024.insights-1.3</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>17</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Fine-tuning a Classifier Help in Low-budget Scenarios? Not Much
%A Gonzalez - Gutierrez, Cesar
%A Primadhanty, Audi
%A Cazzaro, Francesco
%A Quattoni, Ariadna
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fifth Workshop on Insights from Negative Results in NLP
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F gonzalez-gutierrez-etal-2024-fine
%X In recent years, the two-step approach for text classification based on pre-training plus fine-tuning has led to significant improvements in classification performance. In this paper, we study the low-budget scenario, and we ask whether it is justified to allocate the additional resources needed for fine-tuning complex models. To do so, we isolate the gains obtained from pre-training from those obtained from fine-tuning. We find out that, when the gains from pre-training are factored out, the performance attained by using complex transformer models leads to marginal improvements over simpler models. Therefore, in this scenario, utilizing simpler classifiers on top of pre-trained representations proves to be a viable alternative.
%R 10.18653/v1/2024.insights-1.3
%U https://aclanthology.org/2024.insights-1.3
%U https://doi.org/10.18653/v1/2024.insights-1.3
%P 17-24
Markdown (Informal)
[Does Fine-tuning a Classifier Help in Low-budget Scenarios? Not Much](https://aclanthology.org/2024.insights-1.3) (Gonzalez - Gutierrez et al., insights-WS 2024)
ACL