@inproceedings{babic-etal-2026-semtechlab,
    title = "{S}em{T}ech{L}ab at {S}em{E}val-2026 Task 5: Context-Aware Homonym Disambiguation via Span-Specific Interaction Features",
    author = "Babi{\'c}, Karlo  and
      Me{\v{s}}trovi{\'c}, Ana  and
      Beliga, Slobodan",
    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-1.284/",
    pages = "2245--2250",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents the SemTechLab system submitted to SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Sentences through Narrative Understanding. The task involves predicting the plausibility of a specific word sense given a short story context. Our approach (HINTS) utilizes a hybrid Transformer architecture based on nli-mpnet-base-v2. Unlike standard Cross-Encoders that rely solely on the [CLS] token, HINTS extracts span-specific embeddings for the target homonym from both the narrative context and the sense definition. We compute interaction features (concatenation, difference, and element-wise product) between these spans to explicitly model the semantic alignment between the story and the proposed sense. The model is trained using Kullback-Leibler Divergence to predict the full distribution of human ratings. For the official submission phase, scores were rounded to integers (1{--}5). However, subsequent analysis and ablation studies detailed in this paper utilize continuous (float) scores derived from the expected value for improved metric sensitivity. On the test set, our best configuration, which relies exclusively on local homonym features, achieved a Spearman correlation of 0.603 and an accuracy of 75.8{\%}."
}