@inproceedings{papadopoulou-etal-2025-brightcookies,
title = "{B}right{C}ookies at {S}em{E}val-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification",
author = {Papadopoulou, Foteini and
Mutlu, Osman and
{\"O}zen, Neris and
Van Der Velden, Bas and
Hendrickx, Iris and
Hurriyetoglu, Ali},
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.124/",
pages = "914--930",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents our system developed for the SemEval-2025 Task 9: The Food Hazard Detection Challenge. The shared task{'}s objective is to evaluate explainable classification systems for classifying hazards and products in two levels of granularity from web-collected food recall incident reports. In this work, we propose text augmentation techniques as a way to improve poor performance in minority classes and compare their effect for each category on various transformer and machine learning models. We apply three word-level data augmentation techniques, namely synonym replacement, random word swapping, and contextual word insertion utilizing BERT. The resultsshow that transformer models tend to have a better overall performance. Meanwhile, a statistically significant improvement (P 0.05) was observed in the fine-grained categories when using BERT to compare the baseline model with the three augmented models, which achieved a 6{\%} increase in correct predictions for minority hazard classes. This suggests that targeted augmentation of minority classes can improve the performance of transformer models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papadopoulou-etal-2025-brightcookies">
<titleInfo>
<title>BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Foteini</namePart>
<namePart type="family">Papadopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Mutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neris</namePart>
<namePart type="family">Özen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bas</namePart>
<namePart type="family">Van Der Velden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Hendrickx</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hurriyetoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>This paper presents our system developed for the SemEval-2025 Task 9: The Food Hazard Detection Challenge. The shared task’s objective is to evaluate explainable classification systems for classifying hazards and products in two levels of granularity from web-collected food recall incident reports. In this work, we propose text augmentation techniques as a way to improve poor performance in minority classes and compare their effect for each category on various transformer and machine learning models. We apply three word-level data augmentation techniques, namely synonym replacement, random word swapping, and contextual word insertion utilizing BERT. The resultsshow that transformer models tend to have a better overall performance. Meanwhile, a statistically significant improvement (P 0.05) was observed in the fine-grained categories when using BERT to compare the baseline model with the three augmented models, which achieved a 6% increase in correct predictions for minority hazard classes. This suggests that targeted augmentation of minority classes can improve the performance of transformer models.</abstract>
<identifier type="citekey">papadopoulou-etal-2025-brightcookies</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.124/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>914</start>
<end>930</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification
%A Papadopoulou, Foteini
%A Mutlu, Osman
%A Özen, Neris
%A Van Der Velden, Bas
%A Hendrickx, Iris
%A Hurriyetoglu, Ali
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F papadopoulou-etal-2025-brightcookies
%X This paper presents our system developed for the SemEval-2025 Task 9: The Food Hazard Detection Challenge. The shared task’s objective is to evaluate explainable classification systems for classifying hazards and products in two levels of granularity from web-collected food recall incident reports. In this work, we propose text augmentation techniques as a way to improve poor performance in minority classes and compare their effect for each category on various transformer and machine learning models. We apply three word-level data augmentation techniques, namely synonym replacement, random word swapping, and contextual word insertion utilizing BERT. The resultsshow that transformer models tend to have a better overall performance. Meanwhile, a statistically significant improvement (P 0.05) was observed in the fine-grained categories when using BERT to compare the baseline model with the three augmented models, which achieved a 6% increase in correct predictions for minority hazard classes. This suggests that targeted augmentation of minority classes can improve the performance of transformer models.
%U https://aclanthology.org/2025.semeval-1.124/
%P 914-930
Markdown (Informal)
[BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification](https://aclanthology.org/2025.semeval-1.124/) (Papadopoulou et al., SemEval 2025)
ACL