@inproceedings{konle-jannidis-2026-cophiwue,
    title = "{C}ophi{W}ue at {S}em{E}val-2026 Task 4: Symbolic Narrative Profiling with Taxonomy-Guided Extraction and Contrastive Fine-Tuning",
    author = "Konle, Leonard  and
      Jannidis, Fotis",
    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-1.430/",
    pages = "3479--3484",
    ISBN = "979-8-89176-414-9",
    abstract = "We present our system for SemEval-2026 Task 4, focusing primarily on Track B (narrative embedding). Our approach, the Decompose {\&} Align Cycle, converts each story into a structured NarrativeProfile consisting of abstract themes, a five-step course of action, and an outcome. We then build a NarrativeTaxonomy from these initial extractions via agglomerative clustering, and use the resulting controlled vocabularies to guide a second extraction pass, producing terminologically standardized profiles across the full dataset. Finally, we contrastively fine-tune the Qwen3-Embedding8B model on profile text representations using TripletLoss, deriving story embeddings from this fine-tuned model. For Track A, we adapt the task{'}s provided baseline script by substituting Gemini 3 Pro as the judge, using the organizers default prompt on raw story texts."
}