Where the map comes from
The idea: Words that fill the same blanks get pulled together. Predicting the next word, over and over, learns the map — no dictionary needed.
What you'll be able to do: You can explain how a model learns word meanings: words used in similar contexts end up with similar vectors (the distributional hypothesis).
The problem it solves: Lesson 1.1 handed you a finished map of word meanings. But nobody drew it. So where did it come from?
Builds on: Words have no math, Gradient descent: rolling downhill
← Gradient descent: rolling downhill · Next: The context wall →
All lessons