@inproceedings{nodland-2023-training,
    title = "Training and Evaluating {N}orwegian Sentence Embedding Models",
    author = "N{\o}dland, Bernt Ivar Utst{\o}l",
    editor = {Alum{\"a}e, Tanel  and
      Fishel, Mark},
    booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, Faroe Islands",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.nodalida-1.23/",
    pages = "228--237",
    abstract = "We train and evaluate Norwegian sentence embedding models using the contrastive learning methodology SimCSE. We start from pre-trained Norwegian encoder models and train both unsupervised and supervised models. The models are evaluated on a machine-translated version of semantic textual similarity datasets, as well as binary classification tasks. We show that we can train good Norwegian sentence embedding models, that clearly outperform the pre-trained encoder models, as well as the multilingual mBERT, on the task of sentence similarity."
}