@inproceedings{glisic-etal-2025-testing,
    title = "Testing relevant linguistic features in automatic {CEFR} skill level classification for {Icelandic}",
    author = "Gli{\v{s}}i{\'c}, Isidora  and
      Richter, Caitlin Laura  and
      Ingason, Anton Karl",
    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-1.22/",
    pages = "217--222",
    ISBN = "978-9908-53-109-0",
    abstract = "This paper explores the use of various linguistic features to develop models for automatic classification of language proficiency on the CEFR scale for Icelandic, a low-resourced and morphologically complex language. We train two classifiers to assess skill level of learner texts. One is used as a baseline and takes in the original unaltered text written by a learner and uses predominantly surface features to assess the level. The other uses both surface and other morphological and lexical features, as well as context vectors from transformer (IceBERT). It takes in both the original and corrected versions of the text and takes into account errors/deviation of the original texts compared to the corrected versions. Both classifiers show promising results, with baseline models achieving between 62.2-67.1{\%} accuracy and dual-version between 75-80.3{\%}."
}