Artificial Intelligence / Unit 9 AI 0503 worked example, 60 to 90 seconds
The Bigram Table
The idea
Counting how often each word follows each word in a pile of text yields a working language model — the bigram model, built from shares alone.
In practice
The corpus, four sentences whole: the cat sat; the cat purred; the dog sat; the dog ran. Count the pairs. After "the": cat twice, dog twice — shares one half and one half. After "cat": sat one half, purred one half. After "dog": sat one half, ran one half. That table is a language model. And it already generates: start at "the," sample from its column, move to the sampled word, repeat. "The cat purred." "The dog sat." Fluent, at toy scale, by counting alone — no grammar written anywhere, no meanings defined, arithmetic on a four-sentence world.
Where people slip
Every share is a Unit 6 count wearing a new job title — the model is only as wide as its table.
Your place on the trail
Every lesson rests on earlier ones and opens later ones. Tap any to jump.
Unlocks
Something wrong in this lesson? Flag it · Sources for Artificial Intelligence