@inproceedings{dharpure-rusnachenko-2026-hdharpure,
    title = "hdharpure at {S}em{E}val-2026 Task 3: {BERT}-Based Modeling and Prediction Behavior Analysis for Multilingual Valence{--}Arousal Scoring",
    author = "Dharpure, Harshal  and
      Rusnachenko, Nicolay",
    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-1.281/",
    pages = "2228--2232",
    ISBN = "979-8-89176-414-9",
    abstract = "The SemEval-2026 Task 3 is a Dimensional aspect-based sentiment analysis (DimABSA) task which extends traditional ABSA by predicting continuous regression in two dimensions: valence (V) and arousal (A). The Track A/Subtask 1 represent multilingual task in which for a given text and aspects mentioned in it, there is a need to predict V/A scores for each aspect. Our approach is based on the pretraining-finetuning concept: we first pretrain multilingual model (M `) followed by its fine-tuning (M `' l,d) on the training data of specific domain (d) and language (l). We adopt XLM-RoBERTa (M ) as the encoder with separate regression heads for valence and arousal prediction. Our experiments on manual split of official SemEval-2026 Task 3 dataset (D20{\%} train) demonstrate that fine-tuning model in two stages (M `' l,d) results in average {\ensuremath{\approx}} 1.36 times improvement by RMSEva over approach of direct fine-tuning (Ml,d). To investigate limitations of the existing approach we visualize and discuss limitations of our system. Our code is publicly available."
}