Skip to content
ml-recall

#context-window

3 questions from Text Representation & Embeddings, LLM Fundamentals & Prompting

Timed test

3 questions · 3 min · score and explanations at the end

Take a test
Q 1 / 3Score 0 / 0

Question 1: Short answer

mediumAI-checkedText Representation & Embeddings

A skip-gram implementation picks, for every center word, a random window size RR uniformly from {1,2,3,4,5}\{1, 2, 3, 4, 5\} and uses the RR words before and the RR words after it as targets. On average, how many (center, context) training pairs does a word far from the edges of the text produce?

a number