When I train a word2vec model in Gensim on a huge amount of words/data (let's say hundreds of thousands of word vectors), is gensim using negative sampling automatically?
Alternatively, is there a way to make it use it?
$\begingroup$
$\endgroup$
$\begingroup$
$\endgroup$
Gensim's word2vec can use negative sampling. When calling class gensim.models.word2vec.Word2Vec, there is a parameter negative. The default amount is negative=5.
negative (int, optional) – If > 0, negative sampling will be used, the int for negative specifies how many “noise words” should be drawn (usually between 5-20). If set to 0, no negative sampling is used.
The documentation is here.
answered Jul 17 '19 at 14:33
-
$\begingroup$ Please correct me if I'm wrong: the default is the number of 'negative' observations sampled for the logistic regression, right? $\endgroup$ – Leevo Jul 17 '19 at 14:45
