@inproceedings{iqbal-etal-2026-clrg,
title = "{CLRG} at {S}em{E}val-2026 Task 3: One Size Does Not Fit All: A Resource Adaptive Framework for Dimensional Sentiment Regression",
author = "Iqbal, Wardat and
Naswan, Ruwad and
Shatabda, Swakkhar",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.404/",
pages = "3225--3231",
ISBN = "979-8-89176-414-9",
abstract = "Predicting continuous Valence and Arousal scores across diverse languages poses significant challenges due to typological differences and the difficulty of modeling affective intensity. We introduce AdaptStance, a parameter-efficient framework designed for the SemEval-2026 Task 3 benchmark. To address cross-lingual disparities, AdaptStance routes inputs through resource-specific pipelines: direct regression with a hybrid concordance loss for high-resource languages, and an auxiliary multi-task mechanism to stabilize regression in low-resource and non-Western contexts. Architectural analysis reveals that decoupling task heads benefits morphologically related languages, whereas joint representations act as crucial regularizers for distant language families. Ultimately, this lightweight approach achieves competitive performance over generative baselines, demonstrating the efficacy of targeted architectural alignment while identifying Valence as the primary bottleneck in continuous affect prediction. Our code is available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iqbal-etal-2026-clrg">
<titleInfo>
<title>CLRG at SemEval-2026 Task 3: One Size Does Not Fit All: A Resource Adaptive Framework for Dimensional Sentiment Regression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wardat</namePart>
<namePart type="family">Iqbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruwad</namePart>
<namePart type="family">Naswan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swakkhar</namePart>
<namePart type="family">Shatabda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</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">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Predicting continuous Valence and Arousal scores across diverse languages poses significant challenges due to typological differences and the difficulty of modeling affective intensity. We introduce AdaptStance, a parameter-efficient framework designed for the SemEval-2026 Task 3 benchmark. To address cross-lingual disparities, AdaptStance routes inputs through resource-specific pipelines: direct regression with a hybrid concordance loss for high-resource languages, and an auxiliary multi-task mechanism to stabilize regression in low-resource and non-Western contexts. Architectural analysis reveals that decoupling task heads benefits morphologically related languages, whereas joint representations act as crucial regularizers for distant language families. Ultimately, this lightweight approach achieves competitive performance over generative baselines, demonstrating the efficacy of targeted architectural alignment while identifying Valence as the primary bottleneck in continuous affect prediction. Our code is available on GitHub.</abstract>
<identifier type="citekey">iqbal-etal-2026-clrg</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.404/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3225</start>
<end>3231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLRG at SemEval-2026 Task 3: One Size Does Not Fit All: A Resource Adaptive Framework for Dimensional Sentiment Regression
%A Iqbal, Wardat
%A Naswan, Ruwad
%A Shatabda, Swakkhar
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F iqbal-etal-2026-clrg
%X Predicting continuous Valence and Arousal scores across diverse languages poses significant challenges due to typological differences and the difficulty of modeling affective intensity. We introduce AdaptStance, a parameter-efficient framework designed for the SemEval-2026 Task 3 benchmark. To address cross-lingual disparities, AdaptStance routes inputs through resource-specific pipelines: direct regression with a hybrid concordance loss for high-resource languages, and an auxiliary multi-task mechanism to stabilize regression in low-resource and non-Western contexts. Architectural analysis reveals that decoupling task heads benefits morphologically related languages, whereas joint representations act as crucial regularizers for distant language families. Ultimately, this lightweight approach achieves competitive performance over generative baselines, demonstrating the efficacy of targeted architectural alignment while identifying Valence as the primary bottleneck in continuous affect prediction. Our code is available on GitHub.
%U https://aclanthology.org/2026.semeval-1.404/
%P 3225-3231
Markdown (Informal)
[CLRG at SemEval-2026 Task 3: One Size Does Not Fit All: A Resource Adaptive Framework for Dimensional Sentiment Regression](https://aclanthology.org/2026.semeval-1.404/) (Iqbal et al., SemEval 2026)
ACL