0
$\begingroup$

Some programm should allow users to identify the word language probability. All i have is some statistics - the frequency of using bigrams and trigrams in most of texts of some languages.

Totally i have

Top English bigrams Top Spanish bigrams ... th de ... he es ... in en ... er el ... ... ... ...

So how can i calculate the probability, that the word is of language?

`

$\endgroup$
4
  • 1
    $\begingroup$ Do you have a precise definition of "word language probability"? Is it the probability that some word belongs to a language? What do you mean by "the probability, that the word is of language"? $\endgroup$
    – fade2black
    Aug 13, 2017 at 8:40
  • $\begingroup$ yes, sorry, probability that some word belongs to a language $\endgroup$ Aug 13, 2017 at 8:42
  • 1
    $\begingroup$ The first step is to come up with a generative model for words in a language. This will probably require you to assign probabilities for the bigrams or trigrams. $\endgroup$ Aug 13, 2017 at 20:52
  • $\begingroup$ cs.stackexchange.com/q/66475/755 $\endgroup$
    – D.W.
    Aug 14, 2017 at 4:07

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.