@inproceedings{belfathi-etal-2025-simple,
    title = "A Simple but Effective Context Retrieval for Sequential Sentence Classification in Long Legal Documents",
    author = "Belfathi, Anas  and
      Hernandez, Nicolas  and
      Laura, Monceaux  and
      Dufour, Richard",
    editor = "Chistova, Elena  and
      Cimiano, Philipp  and
      Haddadan, Shohreh  and
      Lapesa, Gabriella  and
      Ruiz-Dolz, Ramon",
    booktitle = "Proceedings of the 12th Argument mining Workshop",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.argmining-1.15/",
    doi = "10.18653/v1/2025.argmining-1.15",
    pages = "160--167",
    ISBN = "979-8-89176-258-9",
    abstract = "Sequential sentence classification extends traditional classification, especially useful when dealing with long documents. However, state-of-the-art approaches face two major challenges: pre-trained language models struggle with input-length constraints, while proposed hierarchical models often introduce irrelevant content. To address these limitations, we propose a simple and effective document-level retrieval approach that extracts only the most relevant context. Specifically, we introduce two heuristic strategies: \textbf{Sequential}, which captures local information, and \textbf{Selective}, which retrieves the semantically similar sentences. Experiments on legal domain datasets show that both heuristics lead to consistent improvements over the baseline, with an average increase of ${\sim}5.5$ weighted-F1 points. Sequential heuristics outperform hierarchical models on two out of three datasets, with gains of up to ${\sim}1.5$, demonstrating the benefits of targeted context."
}