bmschmidt/wordVectors

input text file

Opened this issue · 1 comments

I was using train_word2vec function to train vector.
But I was wondering that what is the best input text form.
Should I separate sentence line-by-line? Would it interfere training?

What is the algorithm for dealing space or Line break ?

Thank you.

I find the solution that parameter in the train_word2vec function (threads ) is not set to one.
So that the result is different every time. Once set to one, the result shows that space and Line break does not interfere result.