The KIWI project developed a platform called OntoExtractor enabling semi-automatic extraction of ontologies. This platform is composed of different modules. A first module extract typical instances from a data flow. A second module propose some topological relations among the detected classes. A third module assist the knowledge engineer in transforming classes and relations tentatively proposed by the system in a standard knowledge representation format. This paper address the specific problem of detecting is-a and part-of relations among typical instances of a document base.
Detecting is-a and part-of relations in heterogeneous data flow / P. Ceravolo, D. Rocacher - In: Knowledge-based intelligent information and engineering systems : 9. international conference, KES 2005 : Melbourne, Australia, september 14-16, 2005 : proceedings / [a cura di] Rajiv Khosla, Robert J. Howlett, Lakhmi C. Jain. - Berlin : Springer, 2005. - ISBN 9783540188947. - pp. 104-111 (( Intervento presentato al 9. convegno International Conference on Knowledge-Based Intelligent Information and Engineering Systems tenutosi a Melbourne nel 2005.
Detecting is-a and part-of relations in heterogeneous data flow
P. CeravoloPrimo
;
2005
Abstract
The KIWI project developed a platform called OntoExtractor enabling semi-automatic extraction of ontologies. This platform is composed of different modules. A first module extract typical instances from a data flow. A second module propose some topological relations among the detected classes. A third module assist the knowledge engineer in transforming classes and relations tentatively proposed by the system in a standard knowledge representation format. This paper address the specific problem of detecting is-a and part-of relations among typical instances of a document base.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.