@inproceedings{hikal-etal-2026-logsigma,
    title = "{L}og{S}igma at {S}em{E}val-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis",
    author = "Hikal, Baraa  and
      Becker, Jonas  and
      Gipp, Bela",
    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-1.165/",
    pages = "1237--1257",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1{--}9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters (log {\ensuremath{\sigma}}{\texttwosuperior}) to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence{--}Arousal difficulty profiles{---}from 0.66{\texttimes} for German to 2.18{\texttimes} for English{---}demonstrating that optimal task balancing is language-dependent and cannot be determined a priori."
}