A text preprocessing approach for efficacious information retrieval

Abstract

The information retrieval is the task of obtaining relevant information from a large collection of databases. Preprocessing plays an important role in information retrieval to extract the relevant information. In this paper, a text preprocessing approach text preprocessing for information retrieval (TPIR) is proposed. The proposed approach works in two steps. Firstly, spell check utility is used for enhancing stemming and secondly, synonyms of similar tokens are combined. In this paper, proposed technique is applied to a case study on International Monetary Fund. The experimental results prove the efficiency of the proposed approach in terms of complexity, time and performance.