---
title: "Pixel Phantoms at SemEval-2026 Task 3: Language-Specific"
description: "The paper describes the Pixel Phantoms entry for Subtask 1 of SemEval-2026 Task 3 (DimABSA). 12 references, cited by 1 paper here."
authors: ["Jithu Morrison S", "Abisha Rose S"]
year: 2026
venue: "Proceedings of the 20th International Workshop on Semantic Evaluation (2026)"
source: "https://aclanthology.org/2026.semeval-1.112/"
doi: "10.18653/v1/2026.semeval-1.112"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/s-2026-pixel-phantoms-semeval-2026-task/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/s-2026-pixel-phantoms-semeval-2026-task/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/) / Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis

# Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis

**Authors:** [Jithu Morrison S](https://md.research.elamur.ai/free/en/authors/jithu-morrison-s/) and Abisha Rose S · **Year:** 2026 · **Venue:** [Proceedings of the 20th International Workshop on Semantic Evaluation (2026)](https://md.research.elamur.ai/free/en/venues/semeval/) ([SemEval 2026](https://md.research.elamur.ai/free/en/venues/semeval/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.semeval-1.112/) · [PDF](https://aclanthology.org/2026.semeval-1.112.pdf) · [DOI 10.18653/v1/2026.semeval-1.112](https://doi.org/10.18653/v1/2026.semeval-1.112) · [OpenAlex](https://openalex.org/W7166884929)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper describes the Pixel Phantoms entry for Subtask 1 of SemEval-2026 Task 3 (DimABSA). In this subtask, systems assign continuous Valence and Arousal scores on a 1–9 scale to given aspect terms, replacing discrete polarity labels. The team submitted to every language–domain pair in Track A and Track B, 15 combinations in total. Instead of using one multilingual encoder everywhere, they picked a pretrained backbone per language: deberta-v3-base, cl-tohoku/bert-base-japanese-v3, DeepPavlov/rubert-base-cased, bert-base-chinese, and Davlan's Swahili mBERT. For Ukrainian, Tatar and Nigerian Pidgin they fell back to xlm-roberta-base. Every backbone uses the same regression head:

* the aspect is placed in front of the review as a prompt;
* the CLS and mean-pooled vectors are concatenated;
* a sigmoid output is rescaled with learnable scale and shift parameters;
* training uses a 0.7·MSE + 0.3·MAE loss.

The best results were Japanese Hotel (RMSE 0.7297, rank 13/21) and Chinese restaurant (0.9823, against 1.8959 for the Kimi-K2 baseline). The work suggests that dedicated encoders help in well-resourced languages. Low-resource languages and unfamiliar domains remain weak spots.

## Key points
- The architecture went through four versions (V1–V4). The final V4 uses deberta-v3-base, max length 256, LR 1e-5, early-stopping patience 3, gradient clipping and FP16. Learnable scale and shift start at 8.0 and 1.0.
- Ukrainian (restaurant, xlm-roberta-base): RMSE 1.5937, better than the Kimi-K2 baseline at 1.7805. Tatar (2.0729 vs 1.9380) and Russian with rubert (1.7686 vs 1.7768) were worse than or roughly equal to the baseline.
- Track B, compared with Mistral-3 14B:
  - German politics: 1.5509 vs 1.5910, rank 8/12.
  - English environment: clearly worse, 2.0893 vs 1.6430.
- For Japanese, the system used fugashi and ipadic tokenization plus an aspect prompt written in Japanese. In V1, feeding text and aspect as a plain sentence pair worked worse than the prompt format.
- The authors identify three weaknesses: Arousal is harder to predict than Valence, the model cannot tell apart repeated mentions of the same aspect, and low-resource languages remain hard. Their future work includes transferring Russian models to Ukrainian.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works

🧭 Topics (1): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works

## Cite

Cite as: Jithu Morrison S and Abisha Rose S. 2026. Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis. Proceedings of the 20th International Workshop on Semantic Evaluation (2026).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{s2026pixel,
  title = {{Pixel Phantoms at SemEval-2026 Task 3: Language-Specific Transformer Regression for Dimensional Aspect-Based Sentiment Analysis}},
  author = {Jithu Morrison S and Abisha Rose S},
  booktitle = {Proceedings of the 20th International Workshop on Semantic Evaluation (2026)},
  year = {2026},
  doi = {10.18653/v1/2026.semeval-1.112},
  url = {https://doi.org/10.18653/v1/2026.semeval-1.112}
}
```

- [← previous Pinetree at SemEval-2026 Task 7: A Large-Scale Failure Analysis of Cultural Grounding in Language Models](https://md.research.elamur.ai/free/en/papers/yam-2026-pinetree-semeval-2026-task-7/)
- [next → PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs](https://md.research.elamur.ai/free/en/papers/wang-2026-plam-training-free-plateau-guided/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/)

## References

12 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jonas Becker, Liang-Chih Yu, Shamsuddeen Hassan Muhammad, Jan Philip Wahle, Terry Ruas, Idris Abdulmumin, Lung-Hao Lee, Nelson Odhiambo, Lilian Wanzare, Wen-Ni Liu, Tzu-Mi Lin, Zhe-Yu Xu, Ying-Lung Lin, Jin Wang, Maryam Ibrahim Mukhtar, Bela Gipp, and Saif M. Mohammad. 2026. Dimstance: Multilingual… [find](https://scholar.google.com/scholar?q=Jonas+Becker%2C+Liang%2DChih+Yu%2C+Shamsuddeen+Hassan+Muhammad%2C+Jan+Philip+Wahle%2C+Terry+Ruas%2C+Idris+Abdulmumin%2C+Lung%2DHao+Lee%2C+Nelson+Odhiambo%2C+Lilian+Wanzare%2C+Wen%2DNi+Liu%2C+Tzu%2DMi+Lin%2C+Zhe%2DYu+Xu%2C+Ying%2DLung+Li)
2. Alexis Conneau, Kartik Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. [Unsupervised cross-lingual representation learning at scale](https://md.research.elamur.ai/free/en/papers/conneau-2020-unsupervised-cross-lingual-representation-learning/). In Proceedings of ACL.
3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of NAACL.
4. Yue Gao and 1 others. 2022. Aspect-prompted encoding for aspect-based sentiment analysis. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Yue+Gao+and+1+others%2E+2022%2E+Aspect%2Dprompted+encoding+for+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+ACL%2E)
5. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [Deberta: Decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In Proceedings of ICLR.
6. Lung-Hao Lee, Liang-Chih Yu, Natalia Loukashe-vich, Ilseyar Alimova, Alexander Panchenko, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou, Guangmin Zheng, Jin Wang, Sharanya Awasthi, Jonas Becker, Jan Philip Wahle, Terry Ruas, Shamsuddeen Hassan Muhammad, and Saif M. Mohammad. 2026. Dimabsa: Building multilingu… [find](https://scholar.google.com/scholar?q=Lung%2DHao+Lee%2C+Liang%2DChih+Yu%2C+Natalia+Loukashe%2Dvich%2C+Ilseyar+Alimova%2C+Alexander+Panchenko%2C+Tzu%2DMi+Lin%2C+Zhe%2DYu+Xu%2C+Jian%2DYu+Zhou%2C+Guangmin+Zheng%2C+Jin+Wang%2C+Sharanya+Awasthi%2C+Jonas+Becker%2C+Jan+Philip+Wahl)
7. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv. ArXiv:1907.11692.
8. Maria Pontiki, Dimitris Galanis, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. [Semeval-2014 task 4: Aspect based sentiment analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/). In Proceedings of SemEval.
9. Maria Pontiki, Dimitris Galanis, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2016. [Semeval-2016 task 5: Aspect based sentiment analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/). In Proceedings of SemEval.
10. James A. Russell. 1980. A circumplex model of affect. Journal of Personality and Social Psychology, 39(6):1161–1178. [find](https://scholar.google.com/scholar?q=James+A%2E+Russell%2E+1980%2E+A+circumplex+model+of+affect%2E+Journal+of+Personality+and+Social+Psychology%2C+39%286%29%3A1161%E2%80%931178%2E)
11. Amy B. Warriner, Victor Kuperman, and Marc Brysbaert. 2013. Norms of valence, arousal, and dominance for 13,915 english lemmas. Behavior Research Methods. [find](https://scholar.google.com/scholar?q=Amy+B%2E+Warriner%2C+Victor+Kuperman%2C+and+Marc+Brysbaert%2E+2013%2E+Norms+of+valence%2C+arousal%2C+and+dominance+for+13%2C915+english+lemmas%2E+Behavior+Research+Methods%2E)
12. Liang-Chih Yu, Jonas Becker, Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Lung-Hao Lee, Ying-Lung Lin, Jin Wang, Jan Philip Wahle, Terry Ruas, Alexander Panchenko, Ilseyar Alimova, Kai-Wei Chang, Lilian Wanzare, Nelson Odhiambo, Bela Gipp, and Saif M. Mohammad. 2026. SemEval-2026 task 3: Dimension… [find](https://scholar.google.com/scholar?q=Liang%2DChih+Yu%2C+Jonas+Becker%2C+Shamsuddeen+Hassan+Muhammad%2C+Idris+Abdulmumin%2C+Lung%2DHao+Lee%2C+Ying%2DLung+Lin%2C+Jin+Wang%2C+Jan+Philip+Wahle%2C+Terry+Ruas%2C+Alexander+Panchenko%2C+Ilseyar+Alimova%2C+Kai%2DWei+Chang%2C+Li)

*Updated 2 November 2026*