Text Wrapping Approach to natural Language Information retrieval using significant Indicator

This paper continues the advancement of models proposed for Information Retrieval by understanding that, the Information Retrieval task continues to draw attention as the information repositories increase. Knowing that Natural Language presentation of user’s information need help to reduce the complexity of the search process, we propose the use of a well defined Significant Indicator, which uses the relevance index of terms derived from the position of the text, to perform retrieval. This is achieved by initiating a text wrapping process such that document representation in space could algebraically be measured and assigned appropriate function as similarity ratio for Query and Document. Benchmark tools for Information Retrieval were followed and experiment performed using TREC classified data implemented with TRECEVAL shows better performance against some baseline models. The paper suggests further research in the direction of the Significant Indicator as a method for large search space reduction