@inproceedings{bhalgat-etal-2026-pict,
    title = "{PICT} at {S}em{E}val-2026 Task 3: A Transformer-Based System for Dimensional Aspect-Aware Sentiment Regression with Weighted Layer Pooling",
    author = "Bhalgat, Aditya  and
      Jagtap, Omkar  and
      Phakatkar, Anupama",
    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-1.44/",
    pages = "302--307",
    ISBN = "979-8-89176-414-9",
    abstract = "Team PICT{'}s submission for SemEval-2026 Task 3 (DimASR) tackles continuous valence and arousal prediction by heavily focusing on variance reduction and avoiding cross-domain negative transfer. We built strictly domain-isolated pipelines for the Laptop and Restaurant datasets using a RoBERTa-Large backbone. Our architecture extracts a rich feature hierarchy using weighted layer pooling, isolates local context with a [CLS]-driven aspect-aware attention module, and maps to the continuous space using a deep residual regression head. Regularized via R-Drop and SWA, our system achieved 3rd place in the Restaurant domain (RMSE: 1.195) and 9th in the Laptop domain (RMSE: 1.326)."
}