Deep Learning: Prediction of Next Word
Predict the next word !
This is the Capstone Project for the Johns Hopkins University Data Science Specialization, hosted by Coursera in colaboration with SwiftKey.
The goal of this project was to make a Natural Language Processing predictive application that returns a suggestion of the next word based on text that are inputted.
The dataset was obtained from the HC Corpora corpus and contains three text file datasets (Blogs, News, Twitter). The files are provided in German, Russian, Finnish and English. Only the English file was used for this project
The project is divided into three sections:
-
a Milestone report that includes the preparation of the data such as cleaning, transformations and the analysis.
-
the word prediction application
-
a slide deck presentation that explains how the application works and the overall project.
Here is a sneak peak of how the application looks like:
You can access the full project here:
Or see each section separately here:
- Milestone Report: Report
- Slide deck Presentation: Slide deck
- Application: App