@inproceedings{goot-etal-2025-morsed,
    title = "{MorSeD}: {Morphological} Segmentation of {Danish} and its Effect on Language Modeling",
    author = "Goot, Rob van der  and
      Jensen, Anette  and
      Schledermann, Emil Allerslev  and
      Kildeberg, Mikkel Wildner  and
      Larsen, Nicolaj  and
      Zhang, Mike  and
      Bassignana, Elisa",
    editor = "Johansson, Richard  and
      Stymne, Sara",
    booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.nodalida-1.23/",
    pages = "223--229",
    ISBN = "978-9908-53-109-0",
    abstract = "Current language models (LMs) mostly exploit subwords as input units based on statistical co-occurrences of characters. Adjacently, previous work has shown that modeling morphemes can aid performance for Natural Language Processing (NLP) models. However, morphemes are challenging to obtain as there is no annotated data in most languages. In this work, we release a wide-coverage Danish morphological segmentation evaluation set. We evaluate a range of unsupervised token segmenters and evaluate the downstream effect of using morphemes as input units for transformer-based LMs. Our results show that popular subword algorithms perform poorly on this task, scoring at most an F1 of 57.6 compared to 68.0 for an unsupervised morphological segmenter (Morfessor). Furthermore, evaluate a range of segmenters on the task of language modeling."
}