Writing with Chains

Words that follow words

An interactive lesson with 6 steps, about 5 minutes: you predict, drag and solve, with instant feedback on every answer. It runs in your browser and needs JavaScript.

What you’ll learn

• A word-level Markov chain picks each word from those that followed the last one.
• Transition probabilities come from counting word pairs.
• Longer memories give more coherent text but need far more data.

Steps

1. A chain of words
2. Babbling
3. A transition probability
4. A whole sentence
5. Something new
6. Longer memories