QLVL members - Leonie Grön


Leonie Grön studied linguistics and information processing at Saarland University and the University of Cologne. During her Master's, she developed an interest for the computational processing of biomedical text. Recent work includes a tool for the automatic translation of query languages in biomedical databases.

Leonie is currently pursuing a PhD under the supervision of Ann Bertels and Kris Heylen as part of the MARS project.





E-mail: leonie.gron@kuleuven.be
Phone: +32 16 37 75 54
Surface mail: Department of Linguistics, Blijde-Inkomststraat 21 PO Box 03308, B-3000 Leuven, Belgium
Office: room 02.40 of the Faculty of Arts of the University of Leuven



The past years have seen a steady increase in the production of health-related electronic data. As much of the relevant information is given in unstructured free text, such applications depend on methods of Natural Language Processing (NLP) to unlock the relevant information. Patient records, though, are known to employ a language that is not only highly specialized, but also deviates from standard language with regard to lexis and grammar. Above that, the terminology used in the clinical setting has been shown to deviate substantially from the expressions covered by standard ontologies. Existing NLP modules cannot be readily adopted, but must be modified to handle these particular features.

The PhD carried out as part of the MARS project explores lexical variation in a corpus of Dutch clinical records. The underlying hypothesis is that word choices in clinical records differ systematically from standardized medical terminology, and that these choices are triggered by socio-cognitive factors. Based on an empirical investigation of such usage patterns, the dissertation attempts characterization of lexical variation in clinical Dutch, which may serve as input for computational-linguistic approaches to clinical language processing.