Word Prediction System for Text Entry in Hindi

Abstract

Word prediction is treated as an efficient technique to enhance text entry rate. Existing word prediction systems predict a word when a user correctly enters the initial few characters of the word. In fact, a word prediction system fails if the user makes errors in the initial input. Therefore, there is a need to develop a word prediction system that predicts desired words while coping with errors in initial entries. This requirement is more relevant in the case of text entry in Indian languages, which are involved with a large set of alphabets, words with complex characters and inflections, phonetically similar sets of characters, etc. In fact, text composition in Indian languages involves frequent spelling errors, which presents a challenge to develop an efficient word prediction system. In this article, we address this problem and propose a novel word prediction system. Our proposed approach has been tried with Hindi, the national language of India. Experiments with users substantiate 43.77% keystroke savings, 92.49% hit rate, and 95.82% of prediction utilization with the proposed word prediction system. Our system also reduces the spelling error by 89.75%.