@inproceedings{verma-adelani-2025-mcgill,
title = "{M}c{G}ill-{NLP} at {S}em{E}val-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection",
author = "Verma, Vivek and
Adelani, David Ifeoluwa",
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-1.235/",
pages = "1783--1789",
ISBN = "979-8-89176-273-2",
abstract = "In this paper, we present the results of our SemEval-2025 Emotion Detection Shared Task Track A which focuses on multi-label emotion detection. Our team{'}s approach leverages prompting GPT-4o, fine-tuning NLLB- LLM2Vec encoder, and an ensemble of these two approaches to solve Track A. Our ensemble method beats the baseline method that fine-tuned RemBERT encoder in 24 of the 28 languages. Furthermore, our results shows that the average performance is much worse for under-resourced languages in the Afro- Asiatic, Niger-Congo and Austronesia with per- formance scores at 50 F1 points and below."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verma-adelani-2025-mcgill">
<titleInfo>
<title>McGill-NLP at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</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, we present the results of our SemEval-2025 Emotion Detection Shared Task Track A which focuses on multi-label emotion detection. Our team’s approach leverages prompting GPT-4o, fine-tuning NLLB- LLM2Vec encoder, and an ensemble of these two approaches to solve Track A. Our ensemble method beats the baseline method that fine-tuned RemBERT encoder in 24 of the 28 languages. Furthermore, our results shows that the average performance is much worse for under-resourced languages in the Afro- Asiatic, Niger-Congo and Austronesia with per- formance scores at 50 F1 points and below.</abstract>
<identifier type="citekey">verma-adelani-2025-mcgill</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.235/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1783</start>
<end>1789</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T McGill-NLP at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection
%A Verma, Vivek
%A Adelani, David Ifeoluwa
%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 verma-adelani-2025-mcgill
%X In this paper, we present the results of our SemEval-2025 Emotion Detection Shared Task Track A which focuses on multi-label emotion detection. Our team’s approach leverages prompting GPT-4o, fine-tuning NLLB- LLM2Vec encoder, and an ensemble of these two approaches to solve Track A. Our ensemble method beats the baseline method that fine-tuned RemBERT encoder in 24 of the 28 languages. Furthermore, our results shows that the average performance is much worse for under-resourced languages in the Afro- Asiatic, Niger-Congo and Austronesia with per- formance scores at 50 F1 points and below.
%U https://aclanthology.org/2025.semeval-1.235/
%P 1783-1789
Markdown (Informal)
[McGill-NLP at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection](https://aclanthology.org/2025.semeval-1.235/) (Verma & Adelani, SemEval 2025)
ACL