Natural Language Processing for Conceptual Modeling

A semi-automated approach for the design of databases in enhanced-ERD notation is presented. It focuses on the very early stage of the database development which is the stage of user requirement analysis. It is supposed to be used between the requirements determination stage and analysis. The approach provides the opportunity of using natural language text documents as a source of knowledge for semi-automated generation of a conceptual data model. The system performs information extraction by parsing the syntax of the sentences and semantically analyzing their content.