Abstract: Databases have become ubiquitous. Almost all IT applications are storing and retrieving information from databases. Retrieving information from the database requires knowledge of technical languages such as Structured Query Language (SQL). However majority of the users who interact with the databases do not have a technical background and are intimidated by the idea of using languages such as SQL. This has led to the development of a few Natural Language Database Interfaces (NLDBI). A NLDBI allows the user to query the database in a natural language (NL). This dissertation work highlights on architecture of new NLDBI system, which includes designing a grammar which convert NL statement to a machine understandable language like a query which is fired on a database, constructing parse tree/s and analyzing them. In most of the typical NLDBI systems the NL statement is converted into an internal representation based on the syntactic and semantic knowledge of the NL. This representation is then converted into queries using a representation converter. Before a NL query is translated to an equivalent query in technical language like SQL it has to go through various steps. In this paper it highlights the steps of speech tagging followed by tagging of each word of the query, parsing the tagged sentence by a grammar and generating a grammar tree (parse tree) by applying the semantic analysis on that parse tree and finally SQL translator processes the parse tree to obtain the SQL query.

Keywords: Natural Language, Database, SQL Query, Speech tagging, Parse tree.