ML Fill-in-the-Blanks

ML Fill-in-the-Blanks is a natural language processing (NLP) model that was trained to predict the missing word in a sentence. This project uses pre-trained bert-base-uncased as the prediction model.

  • Use ____ (4 underscores) to mark blank space in the text. e.g. Marc is an ____ person
  • Symbols (including period and comma) and special characters are not allowed.
  • Only one word can be predicted at a time. Model will not work on multiple blank spaces.
  • This model is limited, enter simple sentences if possible.
  • This is deployed on a low-tier DigitalOcean droplet. If you're experiencing 50x errors, try on a simpler sentence or refresh your page to try again.
Legend: Predicted Words Attention Words