@inproceedings{frolov-rykov-2026-ssurface3,
title = "ssurface3 at {S}em{E}val-2026 Task 3: Efficient Methods for Multilingual Dimensional Aspect-Based Sentiment Analysis",
author = "Frolov, Anatolii and
Rykov, Elisei",
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-1.365/",
pages = "2910--2919",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our submission to thedimABSA Shared Task (Subtask 1), whichrequires predicting continuous Valence andArousal scores for target aspects in multilin-gual reviews. We evaluate three approaches:prompting-based baselines, a multilingual en-coder model, and a decoder-only LLM withsupervised fine-tuning. Our main focus isefficient adaptation under multilingual datascarcity. We show that compact encoder anddecoder models, when properly fine-tuned,achieve strong performance across languagesand domains. To improve training stability andenforce valid predictions, we use a boundedregression formulation that maps outputs to thetarget score range. We also explore parameter-efficient fine-tuning and intermediate trainingon external affective data. Results show thatprompting-based baselines are substantiallyweaker than supervised models. The mul-tilingual encoder provides a strong and effi-cient baseline, while the best performance isachieved by a compact decoder model withparameter-efficient fine-tuning. Overall, ourfindings highlight the importance of carefulfine-tuning and training design for multilingualdimensional sentiment analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frolov-rykov-2026-ssurface3">
<titleInfo>
<title>ssurface3 at SemEval-2026 Task 3: Efficient Methods for Multilingual Dimensional Aspect-Based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anatolii</namePart>
<namePart type="family">Frolov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisei</namePart>
<namePart type="family">Rykov</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>This paper describes our submission to thedimABSA Shared Task (Subtask 1), whichrequires predicting continuous Valence andArousal scores for target aspects in multilin-gual reviews. We evaluate three approaches:prompting-based baselines, a multilingual en-coder model, and a decoder-only LLM withsupervised fine-tuning. Our main focus isefficient adaptation under multilingual datascarcity. We show that compact encoder anddecoder models, when properly fine-tuned,achieve strong performance across languagesand domains. To improve training stability andenforce valid predictions, we use a boundedregression formulation that maps outputs to thetarget score range. We also explore parameter-efficient fine-tuning and intermediate trainingon external affective data. Results show thatprompting-based baselines are substantiallyweaker than supervised models. The mul-tilingual encoder provides a strong and effi-cient baseline, while the best performance isachieved by a compact decoder model withparameter-efficient fine-tuning. Overall, ourfindings highlight the importance of carefulfine-tuning and training design for multilingualdimensional sentiment analysis.</abstract>
<identifier type="citekey">frolov-rykov-2026-ssurface3</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.365/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2910</start>
<end>2919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ssurface3 at SemEval-2026 Task 3: Efficient Methods for Multilingual Dimensional Aspect-Based Sentiment Analysis
%A Frolov, Anatolii
%A Rykov, Elisei
%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 frolov-rykov-2026-ssurface3
%X This paper describes our submission to thedimABSA Shared Task (Subtask 1), whichrequires predicting continuous Valence andArousal scores for target aspects in multilin-gual reviews. We evaluate three approaches:prompting-based baselines, a multilingual en-coder model, and a decoder-only LLM withsupervised fine-tuning. Our main focus isefficient adaptation under multilingual datascarcity. We show that compact encoder anddecoder models, when properly fine-tuned,achieve strong performance across languagesand domains. To improve training stability andenforce valid predictions, we use a boundedregression formulation that maps outputs to thetarget score range. We also explore parameter-efficient fine-tuning and intermediate trainingon external affective data. Results show thatprompting-based baselines are substantiallyweaker than supervised models. The mul-tilingual encoder provides a strong and effi-cient baseline, while the best performance isachieved by a compact decoder model withparameter-efficient fine-tuning. Overall, ourfindings highlight the importance of carefulfine-tuning and training design for multilingualdimensional sentiment analysis.
%U https://aclanthology.org/2026.semeval-1.365/
%P 2910-2919
Markdown (Informal)
[ssurface3 at SemEval-2026 Task 3: Efficient Methods for Multilingual Dimensional Aspect-Based Sentiment Analysis](https://aclanthology.org/2026.semeval-1.365/) (Frolov & Rykov, SemEval 2026)
ACL