3
$\begingroup$

Like Word2vec is not a single algorithm but combination of two, namely, CBOW and Skip-Gram model; is Doc2Vec also a combination of any such algorithms? Or is it an algorithm in itself?

Improve this question
$\endgroup$

3 Answers 3

Reset to default
4
$\begingroup$

Word2Vec is not a combination of two models, rather both are variants of word2vec. Similarly doc2vec has Distributed Memory(DM) model and Distributed Bag of words (DBOW) model. Based on the context words and the target word, these variants arised.

Note: the name of the model maybe confusing

  • Distriubted Bag of words is similar to Skip-gram model
  • Distributed Memory is similar to Continuous bag of words model
Improve this answer
$\endgroup$
1
$\begingroup$

Documentation says:

Deep learning via the distributed memory and distributed bag of words models from [1], using either hierarchical softmax or negative sampling [2], [3].

Improve this answer
$\endgroup$
3
  • 1
    $\begingroup$ Those are algorithms used for approximation. and you could use hierarchical softmax or negative sampling in any models, CBOW or SG. $\endgroup$
    – chmodsss
    Commented Jul 10, 2017 at 11:43
  • $\begingroup$ Are DM and DBOW deep learning? I have read CBOW and SG uses a shallow neural network to predict word/context. Shouldn't it be the same for Doc2Vec? $\endgroup$
    – Kshitiz
    Commented Jul 10, 2017 at 19:28
  • $\begingroup$ doc2vec uses the same algorithm as word2vec, except that it uses sentence labels. None of the models are deep learning to be specific. As deep learning model should have multiple hidden layers. Since, deep learning is mostly involved with big data and word2vec and doc2vec mostly works with big data, some term it as deep learning model. But actually it is not. $\endgroup$
    – chmodsss
    Commented Jul 11, 2017 at 7:29
1
$\begingroup$

Distributed Memory model preserves the word order in a document whereas Distributed Bag of words just uses the bag of words approach, which doesn't preserve any word order.

This has been explained in details in this research paper.

Improve this answer
$\endgroup$
1
  • $\begingroup$ No problem, and welcome to Data Science! $\endgroup$
    – Stephen Rauch ♦
    Commented Mar 21, 2018 at 4:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.