@inproceedings{mitka-helcl-2026-cuni,
    title = "{CUNI} at {S}em{E}val-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset",
    author = "Mitka, Jan  and
      Helcl, Jindrich",
    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-1.274/",
    pages = "2163--2178",
    ISBN = "979-8-89176-414-9",
    abstract = "We participate in Track B of the SemEval 2026 Task 4 on narrative similarity, focusing on narrative representation learning. We introduce a synthetic dataset designed to disentangle core narrative aspects-abstract theme, course of action, and outcome-and propose a multi-head multi-positive extension of the InfoNCE objective to train aspect-specific embeddings. Our best model achieves 64.25{\textbackslash}{\%} accuracy on the test set. A nearest-centroid analysis indicates partial aspect-specific structure in the submitted checkpoint, while the training dynamics reveal a partial misalignment between the contrastive objective and the triplet-based evaluation protocol."
}