@inproceedings{pub4418,
    series = {Lecture Notes in Artificial Intelligence, LNAI},
    abstract = {Due to the huge amount of text data in the WWW, annotating unstructured text with semantic markup is a crucial topic in Semantic Web research. This work formally analyzes the incorporation of domain ontologies into information extraction tasks in iDocument. Ontology-based information extraction exploits domain ontologies with formalized and structured domain knowledge for extracting domain-relevant information from un-annotated and unstructured text. iDocument provides a pipeline architecture, an extraction template interface and the ability of exchanging domain ontologies for performing information extraction tasks. This work outlines iDocument's ontology-based architecture, the use of SPARQL queries as extraction templates and an evaluation of iDocument in an automatic document annotation scenario.},
    month = {9},
    year = {2009},
    title = {iDocument: Using Ontologies for Extracting and Annotating Information from Unstructured text},
    booktitle = {KI 2009: Advances in Artificial Intelligence. German Conference on Artificial Intelligence (KI-2009), September 15-18, Paderborn, Germany},
    editor = {Bärbel Mersching and Marcus Hund and Zaheer Aziz},
    volume = {5803},
    pages = {249-256},
    isbn = {978-3-642-04616-2},
    publisher = {Springer-Verlag, Heidelberg},
    author = {Benjamin Adrian and Jörn Hees and Ludger van Elst and Andreas Dengel},
    keywords = {Information Extraction, Ontology, Semantic Web, Semantic Annotation, Natural Language Processing}
}