Last active
May 28, 2018 11:11
-
-
Save nkcr/ec2509f8e8737d0969e5a4528c637372 to your computer and use it in GitHub Desktop.
Implementing a CNN for Text Classification.ipynb
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is the source code used to compare word2vec initialization versus not.
In the training section, comment or not the following block of code to have word2vec initialization or not:
The experiments show that using word2vec initialization or not gives the same result.
The following shows accuracy over epochs on 3 runs. One with random initialization of embedding, another with word2vec initialization and another with word2vec initialization but without further learning of embedding parameters:
The one which grows less fast is with the random initialization.
Here is the loss and corresponding colors: