@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://preview.aclanthology.org/ingest-acl-workshops/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."
}