Word-a-Tron

Predictive Text Application

JHU DDS Capstone Project; Spring 2015

• Built off of three, unstructured text files
  • Blogs (1,010,243 lines)
  • News (899,289 lines)
  • Twitter (2,360,149 lines)
• Must predict a word after a word/phrase typed in
• Must have a profanity filter for predicted word

Task is modeling a language with the above corpuses

• Combine, clean, and tokenize files
• Build n-gram tables for prediction
• Prune, aggregate, and simplify tables

What didn't work

• Smoothing (no discernable improvement)
• Interpolation (no discernable improvement)
• Tf-idf ranking (n-grams too short)
• Cosine similarity (n-grams too short)

Keep it Stupid Simple!!!

Katz (Stupid) Backoff

1. Take (at most) last tri-gram, and find highest frequency occurance
2. If tri-gram non-existant, back-off and use bi-gram
3. If bi-gram non-existant, back-off and use uni-gram

Predicted words are scanned for profanity, and any profane words are substituted with @#$%

Application is located at : Word-a-Tron

1. Simply enter a word or phrase in the text box on the left
2. Predicted word will appear on the right after the word/phrase
3. Use the check box to see the top 3 words predicted

Improvements

• Adaptive Learning with user input over time
• Larger corpus of phrases
• Integration of Information Retreival techniques for larger phrases