@inproceedings{saleh-biltawi-2025-htu,
title = "{HTU} at {S}em{E}val-2025 Task 11: Divide and Conquer - Multi-Label emotion classification using 6 {D}ziri{BERT}s submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation.",
author = "Saleh, Abdallah and
Biltawi, Mariam",
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-1.94/",
pages = "675--683",
ISBN = "979-8-89176-273-2",
abstract = "In this paper, the authors address the challenges of multi-label emotion detection in the Algerian dialect by proposing a novel Label-fused Iterative Mask Filling (L-IMF) data augmentation technique combined with a multi-model architecture. The approach leverages DziriBERT, a BERT variant pre-trained on Algerian text, to generate contextually and label-sensitive aug- mented data, mitigating class imbalance while preserving label consistency. The proposed method uses six independent classifiers, each trained on balanced datasets for dedicated la- bel, to improve performance. The results show significant improvement on mutli-label classification task using Deep Learning, with an F1 macro score of 0.536 on the validation dataset and 0.486 on the test dataset, the sys- tem ranked 28/41 on the Algerian dialect score- board; which is more than 7{\%} higher than the task baseline using RemBERT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saleh-biltawi-2025-htu">
<titleInfo>
<title>HTU at SemEval-2025 Task 11: Divide and Conquer - Multi-Label emotion classification using 6 DziriBERTs submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdallah</namePart>
<namePart type="family">Saleh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Biltawi</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>In this paper, the authors address the challenges of multi-label emotion detection in the Algerian dialect by proposing a novel Label-fused Iterative Mask Filling (L-IMF) data augmentation technique combined with a multi-model architecture. The approach leverages DziriBERT, a BERT variant pre-trained on Algerian text, to generate contextually and label-sensitive aug- mented data, mitigating class imbalance while preserving label consistency. The proposed method uses six independent classifiers, each trained on balanced datasets for dedicated la- bel, to improve performance. The results show significant improvement on mutli-label classification task using Deep Learning, with an F1 macro score of 0.536 on the validation dataset and 0.486 on the test dataset, the sys- tem ranked 28/41 on the Algerian dialect score- board; which is more than 7% higher than the task baseline using RemBERT.</abstract>
<identifier type="citekey">saleh-biltawi-2025-htu</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.94/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>675</start>
<end>683</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HTU at SemEval-2025 Task 11: Divide and Conquer - Multi-Label emotion classification using 6 DziriBERTs submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation.
%A Saleh, Abdallah
%A Biltawi, Mariam
%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 saleh-biltawi-2025-htu
%X In this paper, the authors address the challenges of multi-label emotion detection in the Algerian dialect by proposing a novel Label-fused Iterative Mask Filling (L-IMF) data augmentation technique combined with a multi-model architecture. The approach leverages DziriBERT, a BERT variant pre-trained on Algerian text, to generate contextually and label-sensitive aug- mented data, mitigating class imbalance while preserving label consistency. The proposed method uses six independent classifiers, each trained on balanced datasets for dedicated la- bel, to improve performance. The results show significant improvement on mutli-label classification task using Deep Learning, with an F1 macro score of 0.536 on the validation dataset and 0.486 on the test dataset, the sys- tem ranked 28/41 on the Algerian dialect score- board; which is more than 7% higher than the task baseline using RemBERT.
%U https://aclanthology.org/2025.semeval-1.94/
%P 675-683
Markdown (Informal)
[HTU at SemEval-2025 Task 11: Divide and Conquer - Multi-Label emotion classification using 6 DziriBERTs submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation.](https://aclanthology.org/2025.semeval-1.94/) (Saleh & Biltawi, SemEval 2025)
ACL