@inproceedings{hilasaca-sanchez-etal-2026-align,
    title = "Align and Shine: Building High-quality Sentence-aligned Corpora for Multilingual Text Simplification",
    author = "Hilasaca Sanchez, Luis Kenji  and
      Khallaf, Nouran  and
      Sharoff, Serge",
    editor = "Rapp, Reinhard  and
      Terryn, Ayla Rigouts  and
      Sharoff, Serge  and
      Zweigenbaum, Pierre",
    booktitle = "Proceedings of the 19th Workshop on Building and Using Comparable Corpora ({BUCC})",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/cawl-year/2026.bucc-1.8/",
    doi = "10.63317/55pt8xqgkge6",
    pages = "62--71",
    abstract = "Text simplification plays a crucial role in improving the accessibility and comprehensibility of written information for diverse audiences, including language learners and readers with limited literacy. Despite its importance, large-scale, high-quality datasets for training and evaluating text simplification models remain scarce for languages other than English. This paper reports an experimental study on the collection and processing of crowd-sourced simplification data to construct a corpus suitable for both training and testing text simplification systems across multiple languages (Catalan, English, French, Italian and Spanish). We report mechanisms for sentence-level alignment from document-level data. The resulting dataset of the aligned sentence pairs is publicly available."
}