Fine-tuning Fine-tuned Models: Towards a Practical Methodology for Sentiment Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511634" target="_blank" >RIV/00216208:11320/25:10511634 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-981-96-7005-5_1" target="_blank" >https://link.springer.com/chapter/10.1007/978-981-96-7005-5_1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-96-7005-5_1" target="_blank" >10.1007/978-981-96-7005-5_1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fine-tuning Fine-tuned Models: Towards a Practical Methodology for Sentiment Analysis

Popis výsledku v původním jazyce

Sentiment classifiers are typically built by annotating a relatively small data sample and fine-tuning a pre-trained language model. This approach overlooks the opportunity created by the emergence of open-source sentiment classifiers trained on large collections of supervised data from a variety of domains. These models often exhibit superior classification performance and can be used out-of-the-box, but still their performance may be negatively affected by the domain shift. This could potentially be eliminated by annotating in-domain data and further fine-tuning the model, but fine-tuning of the already fine-tuned models has not been investigated in the context of sentiment analysis and has often been unsuccessful for other NLP tasks. This paper presents an experimental analysis of this issue, studying the performance of three off-the-shelf sentiment classifiers fine-tuned using 14 different methods on customer reviews in three languages. The results show that fine-tuning of already fine-tuned model

Název v anglickém jazyce

Fine-tuning Fine-tuned Models: Towards a Practical Methodology for Sentiment Analysis

Popis výsledku anglicky

Sentiment classifiers are typically built by annotating a relatively small data sample and fine-tuning a pre-trained language model. This approach overlooks the opportunity created by the emergence of open-source sentiment classifiers trained on large collections of supervised data from a variety of domains. These models often exhibit superior classification performance and can be used out-of-the-box, but still their performance may be negatively affected by the domain shift. This could potentially be eliminated by annotating in-domain data and further fine-tuning the model, but fine-tuning of the already fine-tuned models has not been investigated in the context of sentiment analysis and has often been unsuccessful for other NLP tasks. This paper presents an experimental analysis of this issue, studying the performance of three off-the-shelf sentiment classifiers fine-tuned using 14 different methods on customer reviews in three languages. The results show that fine-tuning of already fine-tuned model

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Neural Information Processing

ISBN

978-981-9670-04-8

ISSN

—

e-ISSN

—

Počet stran výsledku

16

Strana od-do

1-16

Název nakladatele

Springer

Místo vydání

Singapore

Místo konání akce

Auckland, New Zealand

Datum konání akce

2. 12. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—