@inproceedings{wu-etal-2026-ncl,
    title = "{NCL}-{BU} at {S}em{E}val-2026 Task 3: Fine-tuning {XLM}-{R}o{BERT}a for Multilingual Dimensional Sentiment Regression",
    author = "Wu, Tong  and
      Rusnachenko, Nicolay  and
      Liang, Huizhi(elly)",
    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-1.240/",
    pages = "1911--1918",
    ISBN = "979-8-89176-414-9",
    abstract = "Dimensional Aspect-Based Sentiment Analysis (DimABSA) extends traditional ABSA from categorical polarity labels to continuous valence{--}arousal (VA) regression. This paper describes a system developed for Track A, Subtask 1 (Dimensional Aspect Sentiment Regression), aiming to predict real-valued VA scores in the [1, 9] range for each given aspect in a text. A fine-tuning approach based on XLM-RoBERTa-base is adopted, using dual regression heads with sigmoid-scaled outputs for valence and arousal prediction. Separate models are trained for each language{--}domain pair (English and Chinese across restaurant, laptop, and finance domains), and training and development sets are merged for final test predictions. In development experiments, the fine-tuning approach is compared against several large language models under a few-shot prompting setting, demonstrating that task-specific fine-tuning outperforms these LLM-based methods across all evaluation datasets."
}