Is there any benefits from using Doc2vec for word embedding ( replacing word2vec ) ? in other hand if I train word2vec and doc2vec with the same dataset will I have the same word vectors ?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
As the name implies, doc2vec generates vectors representing documents (sentences, paragraphs) but not single words. So training doc2vec won't give you word vectors but document vectors. This means you can't replace word2vec by doc2vec at all.
Here's how the authors of the underlying paper describe what doc2vec does:
Our algorithm represents each document by a dense vector which is trained to predict words in the document.
