@inproceedings{lin-yu-2026-b,
    title = "{B} {B} at {S}em{E}val-2026 Task 6: A {R}o{BERT}a-based Model with {NLI}-derived Semantic Features for Clarity-Level Classification of Political Question Evasion",
    author = "Lin, Chi-Bo  and
      Yu, Boyang",
    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-1.384/",
    pages = "3060--3067",
    ISBN = "979-8-89176-414-9",
    abstract = "Equivocation and ambiguity are common in political interviews, where public figures often avoid directly answering challenging questions. We present our submission to SemEval-2026 Task 6, Subtask 1 on English political response clarity classification. Our system builds on RoBERTa and incorporates NLI-derived semantic features to distinguish Clear Reply, Ambivalent, and Clear Non-Reply responses. To address class imbalance and performance instability, we explore class weighting, multi-seed ensembling, and a hierarchical two-stage framework with threshold tuning. Our best model achieves 60{\%} macro-F1 on the official test set and 64{\%} macro-F1 on an additional evaluation set, demonstrating stable performance across splits. Our results show that carefully engineered smaller models, combined with structured semantic features and imbalance-aware training, provide an effective and computationally efficient solution under limited training data."
}