@inproceedings{hanif-etal-2025-university,
title = "{U}niversity of {I}ndonesia at {S}em{E}val-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection",
author = "Hanif, Ikhlasul Akmal and
Yulianrifat, Eryawan Presma and
Ongris, Jaycent Gunawan and
Tjitrahardja, Eduardus and
Azmi, Muhammad Falensi and
Naufal, Rahmat Bryan and
Wicaksono, Alfan Farizki",
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-1.279/",
pages = "2149--2164",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents our approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble combining multiple BGE models, where CatBoost serves as the classifier, with different configurations. This ensemble achieves an average F1-macro score of 56.58 across all languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanif-etal-2025-university">
<titleInfo>
<title>University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ikhlasul</namePart>
<namePart type="given">Akmal</namePart>
<namePart type="family">Hanif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eryawan</namePart>
<namePart type="given">Presma</namePart>
<namePart type="family">Yulianrifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaycent</namePart>
<namePart type="given">Gunawan</namePart>
<namePart type="family">Ongris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardus</namePart>
<namePart type="family">Tjitrahardja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Falensi</namePart>
<namePart type="family">Azmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahmat</namePart>
<namePart type="given">Bryan</namePart>
<namePart type="family">Naufal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfan</namePart>
<namePart type="given">Farizki</namePart>
<namePart type="family">Wicaksono</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 approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble combining multiple BGE models, where CatBoost serves as the classifier, with different configurations. This ensemble achieves an average F1-macro score of 56.58 across all languages.</abstract>
<identifier type="citekey">hanif-etal-2025-university</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.279/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2149</start>
<end>2164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection
%A Hanif, Ikhlasul Akmal
%A Yulianrifat, Eryawan Presma
%A Ongris, Jaycent Gunawan
%A Tjitrahardja, Eduardus
%A Azmi, Muhammad Falensi
%A Naufal, Rahmat Bryan
%A Wicaksono, Alfan Farizki
%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 hanif-etal-2025-university
%X This paper presents our approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble combining multiple BGE models, where CatBoost serves as the classifier, with different configurations. This ensemble achieves an average F1-macro score of 56.58 across all languages.
%U https://aclanthology.org/2025.semeval-1.279/
%P 2149-2164
Markdown (Informal)
[University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection](https://aclanthology.org/2025.semeval-1.279/) (Hanif et al., SemEval 2025)
ACL