@inproceedings{gazetas-etal-2026-ails,
    title = "{AILS}-{NTUA} at {S}em{E}val-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis",
    author = "Gazetas, Stavros  and
      Filandrianos, Giorgos  and
      Lymperaiou, Maria  and
      Tzouveli, Paraskevi  and
      Voulodimos, Athanasios  and
      Stamou, Giorgos",
    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-1.163/",
    pages = "1212--1227",
    ISBN = "979-8-89176-414-9",
    abstract = "In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary problems: Dimensional Aspect Sentiment Regression (DimASR), Dimensional Aspect Sentiment Triplet Extraction (DimASTE), and Dimensional Aspect Sentiment Quadruplet Prediction (DimASQP) within a multilingual and multi-domain framework. Our methodology combines fine-tuning of language-appropriate encoder backbones for continuous aspect-level sentiment prediction with language-specific instruction tuning of large language models using LoRA for structured triplet and quadruplet extraction. This unified yet task-adaptive design emphasizes parameter-efficient specialization across languages and domains, enabling reduced training and inference requirements while maintaining strong effectiveness. Empirical results demonstrate that the proposed models achieve competitive performance and consistently surpass the provided baselines across most evaluation settings."
}