@inproceedings{tai-thin-2025-abcd,
title = "{ABCD} at {S}em{E}val-2025 Task 9: {BERT}-based and Generation-based models combine with advanced weighted majority soft voting strategy",
author = "Tai, Le Duc and
Thin, Dang Van",
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-1.107/",
pages = "785--790",
ISBN = "979-8-89176-273-2",
abstract = "This paper illustrates our ABCD team system approach in ACL 2025 - SemEval-2025 Task 9: The Food Hazard Detection Challenge, aim to solving both Task 1: Text classification for food hazard prediction, predicting the type of hazard and product, and Task 2: Food hazard and product ``vector'' detection, predicting the exact hazard and product. Precisely, we received a food report and our system needed to automatically detect which category of hazard and product the food belonged to. However, in Task 2, we must classify the food report into the exact name of the food hazard and category. To tackle Task 1, we implement and investigate various solutions, including (1) experimenting with a large battery of BERT-based models; and (2) utilizing generation-based models, and (3) taking advantage of a custom ensemble learning method. In addition, to address Task 2, we make use of different data augmentation techniques like synonym replacement and back-translation. To enhance the context of input, we cleaned some special characters that bring more clarity into text input. Our best official results on Task 1 and Task 2 are 0.786 and 0.458 in terms of F1-score, respectively{---}finally, our team solution achieved top 8th in task 1 and top 10th in task 2."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tai-thin-2025-abcd">
<titleInfo>
<title>ABCD at SemEval-2025 Task 9: BERT-based and Generation-based models combine with advanced weighted majority soft voting strategy</title>
</titleInfo>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Tai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dang</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Thin</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 illustrates our ABCD team system approach in ACL 2025 - SemEval-2025 Task 9: The Food Hazard Detection Challenge, aim to solving both Task 1: Text classification for food hazard prediction, predicting the type of hazard and product, and Task 2: Food hazard and product “vector” detection, predicting the exact hazard and product. Precisely, we received a food report and our system needed to automatically detect which category of hazard and product the food belonged to. However, in Task 2, we must classify the food report into the exact name of the food hazard and category. To tackle Task 1, we implement and investigate various solutions, including (1) experimenting with a large battery of BERT-based models; and (2) utilizing generation-based models, and (3) taking advantage of a custom ensemble learning method. In addition, to address Task 2, we make use of different data augmentation techniques like synonym replacement and back-translation. To enhance the context of input, we cleaned some special characters that bring more clarity into text input. Our best official results on Task 1 and Task 2 are 0.786 and 0.458 in terms of F1-score, respectively—finally, our team solution achieved top 8th in task 1 and top 10th in task 2.</abstract>
<identifier type="citekey">tai-thin-2025-abcd</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.107/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>785</start>
<end>790</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ABCD at SemEval-2025 Task 9: BERT-based and Generation-based models combine with advanced weighted majority soft voting strategy
%A Tai, Le Duc
%A Thin, Dang Van
%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 tai-thin-2025-abcd
%X This paper illustrates our ABCD team system approach in ACL 2025 - SemEval-2025 Task 9: The Food Hazard Detection Challenge, aim to solving both Task 1: Text classification for food hazard prediction, predicting the type of hazard and product, and Task 2: Food hazard and product “vector” detection, predicting the exact hazard and product. Precisely, we received a food report and our system needed to automatically detect which category of hazard and product the food belonged to. However, in Task 2, we must classify the food report into the exact name of the food hazard and category. To tackle Task 1, we implement and investigate various solutions, including (1) experimenting with a large battery of BERT-based models; and (2) utilizing generation-based models, and (3) taking advantage of a custom ensemble learning method. In addition, to address Task 2, we make use of different data augmentation techniques like synonym replacement and back-translation. To enhance the context of input, we cleaned some special characters that bring more clarity into text input. Our best official results on Task 1 and Task 2 are 0.786 and 0.458 in terms of F1-score, respectively—finally, our team solution achieved top 8th in task 1 and top 10th in task 2.
%U https://aclanthology.org/2025.semeval-1.107/
%P 785-790
Markdown (Informal)
[ABCD at SemEval-2025 Task 9: BERT-based and Generation-based models combine with advanced weighted majority soft voting strategy](https://aclanthology.org/2025.semeval-1.107/) (Tai & Thin, SemEval 2025)
ACL