Keras Deep Learning Cookbook

With embeddings

In the previous recipe, we did not use any embeddings, such as Global Vectors for Word Representation (GloVe) or Word2vec; we will now use pre-trained word embeddings from Keras. Let's reuse the documents and labels from the preceding recipe. The code is as follows:

# define documents documents = ['Well done!',              'Good work',              'Great effort',              'nice work',              'Excellent!',              'Weak',              'Poor effort!',              'not good',              'poor work',              'Could have done better.']  # define class labels labels = array([1, 1, 1, 1, 1, 0, 0, 0, 0, 0])

Keras provides tokenizer APIs for preparing text that can be fit and reused to prepare multiple text documents. A tokenizer is constructed and then fit onto text documents or integer encoded text documents. Here, words ...