The aim of the TANGO project is provide software to allow users to quickly generate ontologies for a chosen domain. The technique that makes TANGO unique is that users can assemble ontologies semi-automatically from a set of tables that covers the domain concepts. In the ideal case, users simply hand the tables to the TANGO system, and TANGO generates the ontology automatically. User direction and correction, however, is often necessary. Thus, TANGO provides tools that allow a user to observe and interact with the processes of (1) converting raw tables to interpreted tables; (2) converting interpreted tables to mini-ontologies that represent just the information in the table; and (3) integrating mini-ontologies with a growing ontology that represents the domain concepts, relationships, and constraints in the tables that have been processed. Along the way, a user can direct and correct the system. We have designed TANGO tools so that the help required is usually minimal, if not non-existent, but always fully controllable. Thus, it is always possible to create an ontology for the chosen domain, and usually to do so quickly—as close to "in no time at all" as reasonably possible.
The Data Extraction Group includes faculty from Brigham Young University's Computer Science Department and Linguistics and English Language Department and from Rensselaer Polytechnic Institute's Electrical, Computer, and Systems Engineering Department.
Here is a short summary of our project.
This material is based upon work supported by the National Science Foundation under Grant Nos. 0414644 and 0414854. Any opinions, findings, and conclusions expressed in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.
|Comments are welcome.|