@inproceedings{andersson-etal-2025-applying,
    title = "Applying and Optimising a Multi-Scale Probit Model for Cross-Source Text Complexity Classification and Ranking in {Swedish}",
    author = {Andersson, Elsa  and
      Falkenjack, Johan  and
      J{\"o}nsson, Arne},
    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/acl-awards-reasoning/2025.nodalida-1.3/",
    pages = "17--27",
    ISBN = "978-9908-53-109-0",
    abstract = "We present results from using Probit models to classify and rank texts of varying complexity from multiple sources. We use multiple linguistic sources including Swedish easy-to-read books and investigate data augmentation and feature regularisation as optimisation methods for text complexity assessment. Multi-Scale and Single Scale Probit models are implemented using different ratios of training data, and then compared. Overall, the findings suggest that the Multi-Scale Probit model is an effective method for classifying text complexity and ranking new texts and could be used to improve the performance on small datasets as well as normalize datasets labelled using different scales."
}