NLP for Information Retrieval using B Trees

Abstract

Information retrieval is very important area in any of the IT applications. Systematic data storage is essential in information retrieval. In conventional method, data is stored in a structured format and retrieved using SQL queries which requires technical knowledge. There is a necessity to retrieve the data using natural language. A hybrid system to query and retrieve the data from the database using natural language is implemented. It is a combination of keyword based and semantic analysis methods. M-way B-tree is used to store the keywords which act as knowledge base. Analysis shows that using B-tree is found to be faster and superior in retrieving information.

A Naive approach: Translation of Natural Language to Structured Query Language

“…Manasamithra et al [10] introduced a hybrid system to use natural language to search and retrieve data from the database. It is a mixture of approaches of keyword and semantic analysis.…”

“…The syntactic information and understanding of the existing database are used by natural language database systems to correctly relate the structure and content of the natural linguistic input to this existing database table. Syntactic knowledge often exists within the program's linguistic component, especially in syntax analyzer, although actual database information is included in the semantic data model [10]. Natural language inquiries turned into structured query language arguments.…”