1
$\begingroup$

My task is to classify some texts. I have used word2vec to represent text words and I pass them to an LSTM as input. Taking into account that texts do not contain the same number of words, is it a good idea to create text features of fixed dimension using the word2vec word representations of the text and then classify the text using these features as an input of a neural network? And in general is it a good idea to create text features using this method?

$\endgroup$

0

You must log in to answer this question.