Coursera Data Science Capstone Project: A Simple Predictive Language Model
Cheng Juan, PhD
20-04-2015
Objectives
- A predictive language model
- Showcase the model with a Shiny App
Detail of prediction process
- The prediction process first starts with trigram and the most frequent word is selected.
- If no result occurs for trigram model, the prediction model backs off to the bigram model and so on.
- Sometimes, there are multiple words with equal frequency. For example, 10 results are found using trigram model. Then the prediction process select the most frequent within these 10 results in bigram model.
Shiny App Instructions
- Access shiny app here
- Key in your desired phrase into the text box
- The app predict the next word and display it