Skip to main content Skip to main navigation

Publication

Information Extraction from Mammogram Reports

Anna Kupsc; Malgorzata Marciniak; Agnieszka Mykowiecka; Jakub Piskorski; Teresa Podsiadly-Marczykowska
In: KONVENS 2004, Vienna, Austria. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS), 2004.

Abstract

In this paper, we present an environment designed for extraction of medical data from mammogram reports. We process data collected from various Polish health care providers and transform them into attribute-value structures, according to a simplified mammographic ontology. We use a general purpose information extraction (IE) platform, SProUT, enriched with domain-specific terms. We adopt a cascaded processing strategy and merge externally the results obtained by IE techniques. To the best of our knowledge, the current project is the first attempt at IE from Polish medical texts.