WORD WISE PREDICTION USING DEEP LEARNING

Abstract

Word wise prediction is an input technology that simplifies the process of typing by suggesting the next word for a user to select, as typing in a conversation consumes time. You might be using it daily when you write texts or emails without realizing it. Most of the keyboards in smart phones suggest next word prediction features. Google also uses next word prediction based on our browsing history. So, preloaded data is also stored in the keyboard function of our smart phones to predict the next word correctly. By predicting the next word in a sequence, the number of keystrokes of the user can be reduced. In this project, we have used a deep learning approach by using Long Short Term Memory(LSTM) technique which gives better prediction accuracy than the machine learning approach. Key Words: Word, technology, smart phones, keystrokes, long short term memory.