Back to Search
Start Over
Sharing Models and Tools for Processing German Clinical Texts.
- Source :
- Studies in Health Technology & Informatics; May2015, Vol. 210, p734-738, 5p, 2 Charts
- Publication Year :
- 2015
-
Abstract
- The automatic processing of non-English clinical documents is massively hampered by the lack of publicly available medical language resources for training, testing and evaluating NLP components. We suggest sharing statistical models derived from access-protected clinical documents as a reasonable substitute and provide solutions for sentence splitting, tokenization and POS tagging of German clinical texts. These three components were trained on the confidential FRAMED corpus, a non-sharable collection of various German-language clinical document types. The models derived there from outperform alternative components from OPENNLP and the Stanford POS tagger, also trained on FRAMED. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09269630
- Volume :
- 210
- Database :
- Complementary Index
- Journal :
- Studies in Health Technology & Informatics
- Publication Type :
- Academic Journal
- Accession number :
- 108834816
- Full Text :
- https://doi.org/10.3233/978-1-61499-512-8-734