@inproceedings{jerdhaf-etal-2022-evaluating,
    title = "Evaluating Pre-Trained Language Models for Focused Terminology Extraction from {S}wedish Medical Records",
    author = "Jerdhaf, Oskar  and
      Santini, Marina  and
      Lundberg, Peter  and
      Bjerner, Tomas  and
      Al-Abasse, Yosef  and
      Jonsson, Arne  and
      Vakili, Thomas",
    editor = "Costa, Rute  and
      Carvalho, Sara  and
      Ani{\'c}, Ana Ostro{\v{s}}ki  and
      Khan, Anas Fahad",
    booktitle = "Proceedings of the Workshop on Terminology in the 21st century: many faces, many places",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2022.term-1.6/",
    pages = "30--32",
    abstract = "In the experiments briefly presented in this abstract, we compare the performance of a generalist Swedish pre-trained language model with a domain-specific Swedish pre-trained model on the downstream task of focussed terminology extraction of implant terms, which are terms that indicate the presence of implants in the body of patients. The fine-tuning is identical for both models. For the search strategy we rely on KD-Tree that we feed with two different lists of term seeds, one with noise and one without noise. Results shows that the use of a domain-specific pre-trained language model has a positive impact on focussed terminology extraction only when using term seeds without noise."
}