@inproceedings{adam-etal-2026-team,
    title = "Team {H}ausa{NLP} at {S}em{E}val-2026 Task 4: Narratives via Semantic Embeddings",
    author = "Adam, Faisal  and
      Aliyu, Lukman  and
      Aji, Sani",
    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-1.7/",
    pages = "48--53",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents Team HausaNLP{'}s submission to SemEval-2026 Task 4 (Track A),which requires identifying the more narrativelysimilar of two candidate stories relative to ananchor. Narrative similarity is defined alongthree dimensions: abstract theme, course ofaction, and story outcomes. We conduct a systematic ablation comparing five approaches:a lexical TF-IDF baseline, two bi-encoderSBERT variants (all-MiniLM-L6-v2 andall-mpnet-base-v2), a paraphrase-focusedembedding model, and a cross-encoder reranker. On the 200-instance development set,all-mpnet-base-v2 achieves the best performance (61.5{\%} accuracy, 61.48 macro-F1), outperforming both TF-IDF (54.5{\%}) and the official SBERT baseline (55.0{\%}). Surprisingly,the cross-encoder re-ranker (55.5{\%}) does notimprove on the bi-encoders, which we attributeto the long-document nature of Wikipedia storysummaries exceeding the model{'}s effective context window. On the official test set, our primary SBERT MiniLM submission achieved61.50{\%} accuracy (33rd of 44 teams). Our erroranalysis over 200 development instances identifies five systematic failure categories, distinctfrom the All Correct / Partial cases, including23 Lexical Trap cases, 23 Hard Cases, and 24Proposed-Recovery cases, thereby informingconcrete directions for future work."
}