Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Assume I have the words A, B and C. In my calculation, occurrences of ABC should have much bigger weight than AB, and occurrences of AB should be much bigger than A.

$W(x,y,z) = P(x)*\frac{1}{111} + P(x,y)*\frac{10}{111} + P(x,y,z)*\frac{100}{111}$

and I apply the context = $\{A, B, C\}$ to function $W$.

$P(x,y)$ means : (number of xy used together) / (count of bigrams)

My question is not about the formula itself, because I have already implemented a much more complicated form of it. However, I cannot write a proper documentation about it. I don't know the math term.

Is there a mathematical term for what $W$ is doing?

"increasing-size-increasing-weight-summing" ?

share|cite|improve this question
"Weighted average". – user1551 Nov 22 '12 at 21:05
Yes, it is weighted average. However isn't there a special name for that when the number of parameters are increasing? I would say P(x), P(x,y) and P(x,y,z) doesn't have the same class. To me weighted average is more like $P(x)*k + P(y)*l + P(z)*m$ – Ali Ok Nov 23 '12 at 0:43

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.