@inproceedings{riewe-perla-filipowska-2026-pueb,
    title = "{PUEB}-{D}im{ASR} at {S}em{E}val-2026 Task 3: Escaping the Mean Regression Trap with Graph-Enhanced Transformers for Dimensional Aspect-Based Sentiment Regression",
    author = "Riewe-Per{\l}a, Oskar  and
      Filipowska, Agata",
    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-1.53/",
    pages = "361--366",
    ISBN = "979-8-89176-414-9",
    abstract = "The DimABSA shared task aims to combine dimensional analysis with Aspect-Based Sentiment Analysis (ABSA). It addresses the lack of continuous sentiment representation, as opposed to categorical labels (e.g., positive, negative, or neutral), and enriches it with an assessment of arousal. Our team{'}s PUEB-DimASR investigates the ``mean-regression trap'' {---} the tendency of standard MSE loss in high-dimensional sentiment tasks to over-predict values closer to the global mean. We propose a two-step advancement in model ar chitecture. First, we enhance baseline Trans formers with Graph Convolutional Networks(GCN) to capture syntactic aspect-sentiment dependencies. Second, we evaluate and recommend a Hybrid loss function that combines Mean Squared Error (MSE) and Concordance Correlation Coefficient (CCC).Our proposed GCN-deBERTa model consistently outperforms the baseline across six target languages. While MSE loss yields the best RMSE scores for English (0.876) and Chinese (0.546), it introduces significant variance collapse, which we successfully mitigated using the Hybrid loss, achieving near-perfect distributional alignment (99.6{\textbackslash}{\%}). Additionally, our model trained with the Hybrid loss achieved the best RMSE scores for Russian (1.136), Tatar (1.207), and Ukrainian (1.178)."
}