LIN, WEI-YU
2019-08-04
This is the Capstone project of Data Science Specialization, offered by Johns Jopkins University on Coursera. https://www.coursera.org/specializations/jhu-data-science?.
The main purpose of this project is to use the corpus provided from SwiftKey, and use previous n words to predict the next word by N-gram model.
Based on single word input to predict next word.
Based on two-word input to predict next word.
Back-off Method: While inputing a sentence, subtract the last two words as 2-gram to run the prediction. If there is no suitable result, the last word is adopted to be used in 1-gram prediction.