Python Deep Learning Projects

Integrating word2vec with CNN

So, the last time we created our word2vec model, we dumped that model into a binary file. Now it's time to use that model as part of our CNN model. We perform this by initializing the W weights in the embeddings to these values.

Since we trained on a very small corpus in our previous word2vec model, let's choose the word2vec model that was pre-trained on the huge corpus. A good strategy is to use fastText embedding, which is trained on documents available online and for 294 languages (https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md). We do this as follows:

1. We will download the English Embedding fastText dataset (https://s3-us-west-1.amazonaws.com/fasttext-vectors/wiki.en.zip)