Skip to content
ml-recall

#good-turing

2 questions from Language Modeling

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

mediumAI-checkedLanguage Modeling

A sample of n=20n = 20 word tokens contains N1=6N_1 = 6 word types seen exactly once, and N0=30N_0 = 30 vocabulary words do not occur at all. Good–Turing estimation gives the unseen words the total probability N1/nN_1 / n, shared equally among them. What probability does each unseen word get?

a probability