A Novel Approach for Lexical Noise Analysis and Measurement in Intelligent Information Retrieval

Abstract

Latent Semantic Indexing (LSI) is a technique used in Information Retrieval (IR) as an alternative to traditional keyword matching search techniques. LSI is a preferred technique as it can cope with problems and inaccuracies that arise due to synonymy and polysemy. In this paper a new philosophy for LSI analysis and evaluation is presented based on the use of image processing tools. The Term Document Matrix (TDM) generated in the LSI process can now be visualized and treated as an image. Once in this form, techniques from image processing can be applied. The new approach has been validated and evaluated using different key performance metrics used in image processing and IR.