@inproceedings{s-s-2026-pixel,
title = "Pixel Phantoms at {S}em{E}val-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis",
author = "S, Jithu Morrison and
S, Abisha Rose",
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-1.112/",
pages = "803--810",
ISBN = "979-8-89176-414-9",
abstract = "Aspect-Based Sentiment Analysis (ABSA) has traditionally relied on discrete polarity labels (positive, negative, or neutral) which fail to capture the continuous, multidimensional nature of human emotion. SemEval-2026 Task 3, Dimensional Aspect-Based Sentiment Analysis (DimABSA), addresses this limitation by requiring systems to predict continuous Valence (pleasantness) and Arousal (intensity) scores on a 1{--}9 scale for specific aspect terms in text, across 15 language{--}domain combinations in two tracks. Prior approaches to multilingual ABSA have largely depended on single generic multilingual encoders applied uniformly across languages, ignoring language-specific linguistic structures. The Pixel Phantoms system takes a language-aware strategy, selecting dedicated language-specific pre-trained transformer models for each language, including {\textbackslash}url{\{}cl-tohoku/bert-base-japanese-v3{\}} for Japanese, {\textbackslash}url{\{}DeepPavlov/rubert-base-cased{\}} for Russian, {\textbackslash}url{\{}bert-base-chinese{\}} for Chinese, and a Davlan Swahili mBERT variant for Swahili, and falling back to {\textbackslash}url{\{}xlm-roberta-base{\}} for morphologically complex low-resource languages such as Tatar and Ukrainian. All models share a common regression architecture: a dual-pooling head combining CLS and mean-pooled representations, trained with a composite MSE + MAE loss and aspect-prompted input formatting. We participated in both Track A (10 combinations) and Track B (5 combinations), with our strongest result in Japanese Hotel (rank 13/21, RMSE 0.7297) and competitive performance in Chinese restaurant (RMSE 0.9823 vs. Baseline Kimi-K2 Thinking 1.8959). We also analyze failure modes in low-resource languages and domain-shifted settings, highlighting where multilingual transfer remains brittle. Overall, the results indicate that language-specific encoders deliver consistent gains over generic multilingual baselines in dimensional sentiment regression."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-s-2026-pixel">
<titleInfo>
<title>Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jithu</namePart>
<namePart type="given">Morrison</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abisha</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">S</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>Aspect-Based Sentiment Analysis (ABSA) has traditionally relied on discrete polarity labels (positive, negative, or neutral) which fail to capture the continuous, multidimensional nature of human emotion. SemEval-2026 Task 3, Dimensional Aspect-Based Sentiment Analysis (DimABSA), addresses this limitation by requiring systems to predict continuous Valence (pleasantness) and Arousal (intensity) scores on a 1–9 scale for specific aspect terms in text, across 15 language–domain combinations in two tracks. Prior approaches to multilingual ABSA have largely depended on single generic multilingual encoders applied uniformly across languages, ignoring language-specific linguistic structures. The Pixel Phantoms system takes a language-aware strategy, selecting dedicated language-specific pre-trained transformer models for each language, including \textbackslashurl{cl-tohoku/bert-base-japanese-v3} for Japanese, \textbackslashurl{DeepPavlov/rubert-base-cased} for Russian, \textbackslashurl{bert-base-chinese} for Chinese, and a Davlan Swahili mBERT variant for Swahili, and falling back to \textbackslashurl{xlm-roberta-base} for morphologically complex low-resource languages such as Tatar and Ukrainian. All models share a common regression architecture: a dual-pooling head combining CLS and mean-pooled representations, trained with a composite MSE + MAE loss and aspect-prompted input formatting. We participated in both Track A (10 combinations) and Track B (5 combinations), with our strongest result in Japanese Hotel (rank 13/21, RMSE 0.7297) and competitive performance in Chinese restaurant (RMSE 0.9823 vs. Baseline Kimi-K2 Thinking 1.8959). We also analyze failure modes in low-resource languages and domain-shifted settings, highlighting where multilingual transfer remains brittle. Overall, the results indicate that language-specific encoders deliver consistent gains over generic multilingual baselines in dimensional sentiment regression.</abstract>
<identifier type="citekey">s-s-2026-pixel</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.112/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>803</start>
<end>810</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis
%A S, Jithu Morrison
%A S, Abisha Rose
%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 s-s-2026-pixel
%X Aspect-Based Sentiment Analysis (ABSA) has traditionally relied on discrete polarity labels (positive, negative, or neutral) which fail to capture the continuous, multidimensional nature of human emotion. SemEval-2026 Task 3, Dimensional Aspect-Based Sentiment Analysis (DimABSA), addresses this limitation by requiring systems to predict continuous Valence (pleasantness) and Arousal (intensity) scores on a 1–9 scale for specific aspect terms in text, across 15 language–domain combinations in two tracks. Prior approaches to multilingual ABSA have largely depended on single generic multilingual encoders applied uniformly across languages, ignoring language-specific linguistic structures. The Pixel Phantoms system takes a language-aware strategy, selecting dedicated language-specific pre-trained transformer models for each language, including \textbackslashurl{cl-tohoku/bert-base-japanese-v3} for Japanese, \textbackslashurl{DeepPavlov/rubert-base-cased} for Russian, \textbackslashurl{bert-base-chinese} for Chinese, and a Davlan Swahili mBERT variant for Swahili, and falling back to \textbackslashurl{xlm-roberta-base} for morphologically complex low-resource languages such as Tatar and Ukrainian. All models share a common regression architecture: a dual-pooling head combining CLS and mean-pooled representations, trained with a composite MSE + MAE loss and aspect-prompted input formatting. We participated in both Track A (10 combinations) and Track B (5 combinations), with our strongest result in Japanese Hotel (rank 13/21, RMSE 0.7297) and competitive performance in Chinese restaurant (RMSE 0.9823 vs. Baseline Kimi-K2 Thinking 1.8959). We also analyze failure modes in low-resource languages and domain-shifted settings, highlighting where multilingual transfer remains brittle. Overall, the results indicate that language-specific encoders deliver consistent gains over generic multilingual baselines in dimensional sentiment regression.
%U https://aclanthology.org/2026.semeval-1.112/
%P 803-810Markdown (Informal)
[Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis](https://aclanthology.org/2026.semeval-1.112/) (S & S, SemEval 2026)
ACL