Henrik Gjerning
April 2016
A word prediction app (link)
Made for Coursera data science specialization, Swiftkey capstone project.
Prediction Algo for automatic text detection:
The subject of this report is data exploration for “autocomplete” keyboard typing. The sponsor,SwiftKey, is known for building smart keyboards that makes it easier for people to type on their mobile devices by second guessing what people are going to type. One cornerstone technology of smart keyboards is the use of predictive text models.
What the Application does:
Based on user inputs sentences This application
will try and prectict the most likely next next word, based on frequently
occurring phrases (n-grams).
Model building stage:
The raw text input from blogs, twitter and news sources
is taken through a multistage cleaning process.This also includes Tokenisation and Lemmatization.
Further Info:
For further interest there is a number of links
it is worth while to take a closer look at.