Skip to content
ml-recall

#negative-sampling

4 questions from Text Representation & Embeddings, Fine-tuning & PEFT

Timed test

4 questions · 4 min · score and explanations at the end

Take a test
Q 1 / 4Score 0 / 0

Question 1: Short answer

easyAI-checkedText Representation & Embeddings

word2vec draws its negative-sampling noise words with probability proportional to their corpus frequency raised to the power 0.75. A tiny vocabulary has two words, with counts 16 and 1. What is the probability of drawing the frequent word? Round to 3 decimals.

a probability, 3 decimals