Search: onr:"swepub:oai:DiVA.org:ri-52378" >
Implant Terms: Focused Terminology Extraction with Swedish BERT - Preliminary Results
-
- Jerdhaf, Oskar (author)
- Linkoping University, Sweden
-
- Santini, Marina, 1960- (author)
- RISE,Prototypande samhälle,Digital Health
-
- Lundberg, Peter (author)
- Linkoping University, Sweden
-
show more...
-
- Karlsson, Anette (author)
- Linkoping University, Sweden
-
- Jönsson, Arne (author)
- Linkoping University, Sweden
-
show less...
-
(creator_code:org_t)
- 2020
- English.
- Related links:
-
https://ri.diva-port... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- Certain implants are imperative to detect be-fore MRI scans. However, implant terms, like‘pacemaker’ or ‘stent’, are sparse and difficultto identify in noisy and hastily written elec-tronic medical records (EMRs). In this pa-per, we explore how to discover implant termsin Swedish EMRs with an unsupervised ap-proach.To this purpose, we use BERT, astate-of-the-art deep learning algorithm, andfine-tune a model built on pre-trained SwedishBERT. We observe that BERT discovers asolid proportion of indicative implant terms.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Keyword
- Automatic Terminology Extraction
- BERT
- medical records
- deep llearning
- pretrained model in Swedish
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database