EMBEC'05. European Medical and Biomedical Conference /3./
Event date
20.11.2005-25.11.2005
VEvent location
Prague
Country
CZ - Czech Republic
Event type
EUR
Language
eng - English
Country
SE - Sweden
Keywords
information extraction ; natural language processing ; machine learning
Subject RIV
BD - Theory of Information
R&D Projects
1ET200300413 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR)
CEZ
AV0Z10300504 - UIVT-O (2005-2011)
Annotation
In the past, the problem of extracting patient data from medical record was solved by writing extraction rules for every element of information that is to be extracted. However, in general such approach is very time consuming and requires supervision of a skilled programmer whenever the target area of medicine or the text corpus are changed. In this article we explore the possibility to mechanize this process by automatically generating the extraction rules from a pre-annotated corpus of medical texts.