Medizinische Universität Graz - Research portal

Go directly to the nagivation.
Go directly to the content.

Navigation/Search

Selected Publication:

SHR Neuro Cancer Cardio Lipid Metab Microb

Abdulnazar, A; Kreuzthaler, M; Roller, R; Schulz, S.
SapBERT-Based Medical Concept Normalization Using SNOMED CT.
Stud Health Technol Inform. 2023; 302: 825-826. Doi: 10.3233/SHTI230278
PubMed FullText FullText_MUG

Leading authors Med Uni Graz: Kuppassery Abdulnazar Akhila Naz
Co-authors Med Uni Graz: Kreuzthaler Markus Eduard; Schulz Stefan
Altmetrics:
Dimensions Citations:
Plum Analytics:
Scite (citation analytics):
Abstract:: Word vector representations, known as embeddings, are commonly used for natural language processing. Particularly, contextualized representations have been very successful recently. In this work, we analyze the impact of contextualized and non-contextualized embeddings for medical concept normalization, mapping clinical terms via a k-NN approach to SNOMED CT. The non-contextualized concept mapping resulted in a much better performance (F1-score = 0.853) than the contextualized representation (F1-score = 0.322).
Find related publications in this database (using NLM MeSH Indexing): Systematized Nomenclature of Medicine - administration & dosage; Natural Language Processing - administration & dosage