Performance Evaluation of Different Similarity Functions and Classification Methods Using Web Based Hindi Language Question Answering System

Question Answering (QA) system is an approach to extract the correct answer for the query asked by the user in its own language. The work discussed is implemented for Hindi Language objective type questions and answers. The paper implements the comparison of nine different similarity functions and two classification methods used to retrieve the desired information. The results revealconclude that Smith Waterman outperforms the other similarity functions in perforamnce evaluation. The K-Nearest Neighbor(K-NN) algorithm gives 97%, 95.6% and Neasret Neighbor (NN) algorithm gives 93.3%,95% for two differtent test data sets, respectively.