A FORM-BASED NATURAL-LANGUAGE FRONT-END TO A CIM DATABASE

This paper presents a methodology for developing a user interface that combines fourth generation interface tools (SQL forms) with a natural language processor for a database management system. The natural lang uage processor consists of an index, a lexicon, and a parser. The inde x is used to uniquely identify each form in the system through a conce ptual representation of its purpose. The form fields specify database or nondatabase fields whose values are either entered by the user (use r-defined) or are derived by the form (system-defined) in response to user input. A set of grammar rules are associated with each form. The lexicon consists of all words recognized by the system, their grammati cal categories, roots, their associations (if any) with database objec ts and forms. The parser scans a natural language query to identify a form in a bottom-up fashion. The information requested in the user que ry is determined in a top-down manner by parsing through the grammar r ules associated with the identified form. Extragrammatical inputs with limited deviations from the grammar rules are supported. Combining a natural language processor with SQL forms allows processing data modif ication tasks without violating any database integrity constraint, hav ing duplicate records, or entering invalid data. A prototype natural l anguage interface is described as a front-end to an ORACLE database fo r a computer integrated manufacturing system.