@inproceedings{laschenko-korotyk-2026-sokratum,
    title = "{S}okra{TUM} at {S}em{E}val-2026 Task 3: A hybrid cascade of Label Distribution Learning, {RAG} supported generative extraction and contrastive metric learning for dimensional sentiment analysis",
    author = "Laschenko, Denis  and
      Korotyk, Albert",
    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/corrections-2026-07/2026.semeval-1.241/",
    doi = "10.18653/v1/2026.semeval-1.241",
    pages = "1919--1929",
    ISBN = "979-8-89176-414-9",
    abstract = "The Dimensional ABSA (DimABSA) shared task extends traditional aspect-based sentiment analysis from categorical polarity to continuous valence{--}arousal (VA) prediction. We present our system for all three subtasks: Dimensional Aspect Sentiment Regression (DimASR), Dimensional Aspect Sentiment Triplet Extraction (DimASTE), and Dimensional Aspect Sentiment Quad Prediction (DimASQP). Due to the cascading nature of the different subtasks, we built a modular interlocking pipeline that uses classical Machine Learning and NLP methods. Experiments across domains show consistent gains in regression accuracy and structured extraction performance. Our results demonstrate the effectiveness of distribution-aware regression, retrieval-augmented generation, and contrastive prototype learning for dimensional sentiment analysis."
}