@inproceedings{soltes-bajec-2006-lightweight,
    title = "A Lightweight N-gram Approach to Abbreviation Expansion in Large Corpora",
    author = "{\v{S}}oltes, Tja{\v{s}}a  and
      Bajec, Marko",
    editor = "Gorman, Kyle",
    booktitle = "Proceedings of the Third Workshop on Computation and Written Language ({CAWL} 2026) @ {LREC} 2026",
    month = jun,
    year = "2006",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.cawl-1.10/",
    doi = "10.63317/3t4xjiz2vvw2",
    pages = "95--100",
    abstract = "We present a lightweight, corpus-based approach to abbreviation expansion that relies solely on contextual N-gram statistics. The method models local context using two-sided and one-sided bigram and trigram counts extracted from a large domain-specific corpus. Candidate expansions are selected through linear interpolation of context-specific evidence, enhanced with reliability-based scaling to mitigate sparse data effects. The approach does not require external linguistic resources, pretrained language models, or explicit morphosyntactic analysis, making it suitable for domain-specific and resource-constrained settings. Experiments conducted on a large Slovene medical corpus demonstrate that interpolation generally outperforms strict backoff strategies, with notable improvements for medium- and low-frequency abbreviations. Despite its simplicity, the proposed framework achieves robust performance while remaining computationally efficient and scalable."
}