Pernille Just Vinholt
2023
Benchmark for Evaluation of Danish Clinical Word Embeddings
Martin Sundahl Laursen
|
Jannik Skyttegaard Pedersen
|
Pernille Just Vinholt
|
Rasmus Søgaard Hansen
|
Thiusius Rajeeth Savarimuthu
Northern European Journal of Language Technology, Volume 9
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.