This repository contains an Information Retrieval System which retrieves relevant documents from Cranfield dataset when provided with required queries/ selecting the existing queries.
The IR systems consists entire pipeline - starting with preprocessing documents and queries, building algorithms that are mainly responsible for extracting documents using TF-IDF, Latent semantic analysis, Query expansion using Wordnet etc ,and evaluation of the end results via multipe metrics such Precision, Recall, MAP, n-DCG.