@article{laursen-etal-2023-benchmark,
    title = "Benchmark for Evaluation of {D}anish Clinical Word Embeddings",
    author = "Laursen, Martin Sundahl  and
      Pedersen, Jannik Skyttegaard  and
      Vinholt, Pernille Just  and
      Hansen, Rasmus S{\o}gaard  and
      Savarimuthu, Thiusius Rajeeth",
    editor = "Derczynski, Leon",
    journal = "Northern European Journal of Language Technology",
    volume = "9",
    year = "2023",
    address = {Link{\"o}ping, Sweden},
    publisher = {Link{\"o}ping University Electronic Press},
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.nejlt-1.4/",
    doi = "10.3384/nejlt.2000-1533.2023.4132",
    abstract = "In natural language processing, benchmarks are used to track progress and identify useful models. Currently, no benchmark for Danish clinical word embeddings exists. This paper describes the development of a Danish benchmark for clinical word embeddings. The clinical benchmark consists of ten datasets: eight intrinsic and two extrinsic. Moreover, we evaluate word embeddings trained on text from the clinical domain, general practitioner domain and general domain on the established benchmark. All the intrinsic tasks of the benchmark are publicly available."
}