iDocument: Using Ontologies for Extracting Information from TextBenjamin 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.