@inproceedings{pham-hoang-le-etal-2025-nta,
title = "{NTA} at {S}em{E}val-2025 Task 11: Enhanced Multilingual Textual Multi-label Emotion Detection via Integrated Augmentation Learning",
author = "Pham Hoang Le, Nguyen and
Nguyen Tran Khuong, An and
Nguyen Thi Ngoc, Tram and
Dang Van, Thin",
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-1.237/",
pages = "1795--1801",
ISBN = "979-8-89176-273-2",
abstract = "Emotion detection in text is crucial for various applications, but progress, especially in multi-label scenarios, is often hampered by data scarcity, particularly for low-resource languages like Emakhuwa and Tigrinya. This lack of data limits model performance and generalizability. To address this, the NTA team developed a system for SemEval-2025 Task 11, leveraging data augmentation techniques: swap, deletion, oversampling, emotion-focused synonym insertion and synonym replacement to enhance baseline models for multilingual textual multi-label emotion detection. Our proposed system achieved significantly higher macro F1-scores compared to the baseline across multiple languages, demonstrating a robust approach to tackling data scarcity. This resulted in a 17th place overall ranking on the private leaderboard, and remarkably, we achieved the highest score and became the winner in Tigrinya language, demonstrating the effectiveness of our approach in a low-resource setting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-hoang-le-etal-2025-nta">
<titleInfo>
<title>NTA at SemEval-2025 Task 11: Enhanced Multilingual Textual Multi-label Emotion Detection via Integrated Augmentation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Pham Hoang Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Nguyen Tran Khuong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tram</namePart>
<namePart type="family">Nguyen Thi Ngoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thin</namePart>
<namePart type="family">Dang Van</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>Emotion detection in text is crucial for various applications, but progress, especially in multi-label scenarios, is often hampered by data scarcity, particularly for low-resource languages like Emakhuwa and Tigrinya. This lack of data limits model performance and generalizability. To address this, the NTA team developed a system for SemEval-2025 Task 11, leveraging data augmentation techniques: swap, deletion, oversampling, emotion-focused synonym insertion and synonym replacement to enhance baseline models for multilingual textual multi-label emotion detection. Our proposed system achieved significantly higher macro F1-scores compared to the baseline across multiple languages, demonstrating a robust approach to tackling data scarcity. This resulted in a 17th place overall ranking on the private leaderboard, and remarkably, we achieved the highest score and became the winner in Tigrinya language, demonstrating the effectiveness of our approach in a low-resource setting.</abstract>
<identifier type="citekey">pham-hoang-le-etal-2025-nta</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.237/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1795</start>
<end>1801</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NTA at SemEval-2025 Task 11: Enhanced Multilingual Textual Multi-label Emotion Detection via Integrated Augmentation Learning
%A Pham Hoang Le, Nguyen
%A Nguyen Tran Khuong, An
%A Nguyen Thi Ngoc, Tram
%A Dang Van, Thin
%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 pham-hoang-le-etal-2025-nta
%X Emotion detection in text is crucial for various applications, but progress, especially in multi-label scenarios, is often hampered by data scarcity, particularly for low-resource languages like Emakhuwa and Tigrinya. This lack of data limits model performance and generalizability. To address this, the NTA team developed a system for SemEval-2025 Task 11, leveraging data augmentation techniques: swap, deletion, oversampling, emotion-focused synonym insertion and synonym replacement to enhance baseline models for multilingual textual multi-label emotion detection. Our proposed system achieved significantly higher macro F1-scores compared to the baseline across multiple languages, demonstrating a robust approach to tackling data scarcity. This resulted in a 17th place overall ranking on the private leaderboard, and remarkably, we achieved the highest score and became the winner in Tigrinya language, demonstrating the effectiveness of our approach in a low-resource setting.
%U https://aclanthology.org/2025.semeval-1.237/
%P 1795-1801
Markdown (Informal)
[NTA at SemEval-2025 Task 11: Enhanced Multilingual Textual Multi-label Emotion Detection via Integrated Augmentation Learning](https://aclanthology.org/2025.semeval-1.237/) (Pham Hoang Le et al., SemEval 2025)
ACL