OntoLT

Middleware for Ontology Extraction from Text

The OntoLT approach aims at a more direct connection between ontology engineering and linguistic analysis. OntoLT is a Protégé plug-in, with which concepts (Protégé classes) and relations (Protégé slots) can be extracted automatically from linguistically annotated text collections. It provides mapping rules, defined by use of a precondition language that allow for a mapping between linguistic entities in text and class/slot candidates in Protégé.

This software and its documentation is freely available, see License Terms

„Version 2.0“ (OntoLT for Protege 3.2) Download -- Please note that OntoLT 2.0 only works with Protege 3.2

Download OntoLT ~2.6 Mb -- includes source, binaries, installation guide and example annotated corpus

Download OntoLT Javadocs

„Version 1.0“ (OntoLT for Protege 1.8) Download

Download OntoLT ~6 Mb -- includes source, binaries, installation guide and example annotated corpus

Download OntoLT Javadocs

Documentation

We recommend reading the following paper on OntoLT:

Paul Buitelaar, Daniel Olejnik, Michael Sintek

A Protégé Plug-In for Ontology Extraction from Text Based on Linguistic Analysis

In: Proceedings of the 1^st European Semantic Web Symposium (ESWS), Heraklion, Greece, May 2004.

Download this Paper and/or the OntoLT User Guide for Version 1.0 (includes some screenshots)

Contact

Please send comments and/or questions to:

Paul Buitelaar, Michael Sintek

DFKI GmbH

Saarbrücken/Kaiserslautern, Germany

Please send bug reports also to: Nicolas Weber

Acknowledgements

Previous versions of OntoLT have been implemented by Daniel Olejnik and were developed under grants IST-2000-29243 for the OntoWeb project and IST-2000-25045 for the MEMPHIS project. Maintenance and extension work by Yasir Iqbal and Nicolas Weber is supported by grants for the projects VIeWs (by the Saarland Ministry of Economic Affairs) and SmartWeb (by the German Ministry of Education and Research: 01 IMD01 A).