basis for Statistical Semantics
a word is characterized by the company it keeps The meaning of a word is its use in the language If A and B have almost identical environments we say that they are synonyms.
Given word w and all the contexts C(w) = {c1 ,c2 ,…} it appears within,
then meaning(w) = f(c1 ,c2 ,…) where f is a function compressing some statistics of C(w) into a vector.