Toward enhanced Natural Language Processing to databases: Building a specific domain Ontology derived from database conceptual model

Natural Language Interface to database NLIDB applications achieve great success when dealing with simple user requests, however most of NLIDB applications fail dramatically when users issue indirect or sophisticated requests. One modern approach to enhance NLIDB is using Ontology. Ontologies are very helpful when used with Natural Language Processing applications for supporting extraction of relevant elements from databases. This paper proposes a framework and a semi automatic procedure for building domain specific Ontology by using data conceptual model and general purpose Ontology such as WordNet. The aim is to help NLIDB understanding and simplifying indirect users data requests.