@inproceedings{jain-etal-2026-rating,
    title = "Rating Plausibility of Word Senses in Ambiguous Sentences Using Multi-Architecture Analysis",
    author = "Jain, Naina  and
      Arora, Nidhi  and
      Thakkar, Pal  and
      Sahu, Siba",
    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-1.292/",
    pages = "2307--2313",
    ISBN = "979-8-89176-414-9",
    abstract = "Word sense disambiguation in narrative contexts requires systems to reason about subtle semantic relationships between candidate senses and discourse context. This paper addresses SemEval 2026 Task 5, which reformulates WSD as a graded plausibility prediction problem on a 1{--}5 Likert scale using the AmbiStory dataset. We present two complementary approaches: (1) a DeBERTa-v3-Large encoder with attention-weighted pooling and ordinal regression, achieving a Spearman correlation of 0.718, and (2) a rank-based ensemble combining FLAN-T5 and RoBERTa, achieving 0.692. Through ablation studies, we show that explicitly modeling ordinal structure improves performance over standard regression by 17.3{\%}. We further analyze the strengths of each approach, showing that fine-tuned encoders capture fine-grained semantic relationships, while ensemble methods provide robustness through complementary modeling biases. Our results provide a detailed empirical analysis of design choices for graded plausibility prediction in narrative understanding."
}