@inproceedings{john-etal-2026-modeling,
    title = "Modeling Word-Internal Structures: Morphological Segmentation Across 58 Languages",
    author = "John, Vojt{\v{e}}ch  and
      {\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k  and
      Reeves, Benjamin",
    editor = "Hinrichs, Erhard  and
      Nivre, Joakim  and
      Osenova, Petya  and
      Pustejovsky, James  and
      Zinn, Claus",
    booktitle = "Proceedings of the Workshop on Structured Linguistic Data and Evaluation ({SL}i{DE})",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-previews/2026.slide-1.16/",
    doi = "10.63317/4qgccaokf8mz",
    pages = "180--190",
    abstract = "We present the largest multilingual experiment to date on word-to-morph segmentation, covering 58 typologically diverse languages. We describe a newly compiled collection of linguistically annotated resources for the task, providing broad coverage and enabling systematic cross-lingual evaluation. Second, we train two neural models on surface morphological segmentation, achieving 81{\%} average word accuracy on the original datasets, slightly outperforming previous methods. Experiments on custom test sets reveal substantial variation in performance, highlighting the need for further harmonization and more robust multilingual approaches."
}