iDocument: Using Ontologies for Extracting Information from Text

Benjamin Adrian; Heiko Maus; Andreas Dengel

In: Barbara Thönssen (Hrsg.). WM2009: 5th Conference on Professional Knowledge Management. Conference on Professional Knowledge Management (WM-09), March 25-27, Solothurn, Switzerland, WM2009: 5th Conference on Professional Knowledge Management, Lecture Notes in Informatics (LNI), Vol. P-145, ISBN 978-3-88579-239-0, GI, 3/2009.


This work outlines system and usage principles of the ontology-based information extraction system iDocument. Ontology-based information extraction reuses existing domain knowledge for extracting and annotating relevant information from domain-related text. iDocument provides an architecture, an API, and a user interface for supporting users and developers in ontology based knowledge annotation and acquisition tasks. The main contribution of this work is a generic and standardized information extraction template interface for retrieving relevant information from text by using existing domain ontologies.


Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence