Querying database using a universal natural language interface based on machine learning

Abstract

Extracting information from a database system becomes a primary obligation. More and more we are forced to recognize the importance of providing easy access to information stored in a database system. However existing tools that allow users to query database using database query languages such as SQL (Structured Query Language) are difficult for non-experts users. Wherefore asking questions to databases in natural language is a very simple method that can provide powerful improvements to the use of data stored in databases. This paper presents the Architecture and the implementation of a generic natural language interface based on machine learning approach for a relational database. The advantage of this interface is that it functions independently of the database domain and automatically improves through experience its knowledge base.