How to use word embedding as a feature ?
somnathasati opened this issue · comments
somnathasati commented
I want to know, if there exist any way to pass word vector extracted from word2vec as a feature ? or, i have to use/change something else in place of existing feature hashing ? Great Thanks !
Mikhail Korobov commented
There is no feature hashing, seqlearn estimators require feature matrix X which can contain arbitrary features, including word vectors.