Since Keras API as defined as layers, how would it be used to implement the word2vec?
$\begingroup$
$\endgroup$
-
$\begingroup$ Hi. This question is more suited to DataScience. $\endgroup$ – Philip Raeisghasem Mar 29 '19 at 17:39
-
$\begingroup$ @PhilipRaeisghasem Is it possible this question is broad enough to qualify as "theory"? $\endgroup$ – DukeZhou♦ Mar 29 '19 at 20:42
-
$\begingroup$ I think any complete answer would need to reference the Keras API, so I still vote to close as off-topic. $\endgroup$ – Philip Raeisghasem Mar 29 '19 at 21:07
$\begingroup$
$\endgroup$
Your question is really broad.. But there are many manuals and tutorials which describe how to do it step by step.
My personal favorite would be:
Practical Text Classification With Python and Keras - It has a very detailed explanation of every step of the implementation while remaining practical.
You can also try:
A Word2Vec Keras tutorial - This one focuses more on understanding how word2vec embedding works, but it also contains an implementation.
$\begingroup$
$\endgroup$
Tensorflow released a version, however, it's missing negative sampling, which is very important in word2vec
