skip-gram-pytorch
skip-gram-pytorch copied to clipboard
Thanks for making this code available
I started off from your code and made a few modifications described in detail on this blog: http://www.telesens.co/2018/02/08/word2vec-experiments/
The major modification was adding the ability to use a pre-trained model as a starting point for training a new model. Combining the vocabularies from the old and new model was a bit tricky.
My code is available here: https://github.com/ankur6ue/word2vec
Thanks again for making your code available. It was relatively easy to understand and modify. Using Pytorch is such a joy!
Regards, Ankur