You have already implemented forward propagation, back propagation, and gradient descent to train the neural network of a continuous bag of words model. But how do you get the word embeddings out of your trained neural nets? As you may remember, word embedding, are not directly outputs by the training process. They are a byproduct of the process. I'll now explain how you can extract word embeddings from a trained neural net. Remember, these are vectors that carry the meaning of the words of the vocabulary based on the context words in the corpus. Once you've trained your neural network, after iterating through all of your training data possibly several times, you can extract three alternative word embedding representations. The first possibility is to consider each column of W_1 as the column vector embedding vector of a word of the vocabulary. Recall that matrix W_1 has v number of columns, so it has one column for each word in the vocabulary. The mapping between columns of W_1 and words, uses the same order as the input rows. For example, with the corpus, I am happy because I'm learning and the five rows of the input vector or matrix corresponds to m because happy, I, and learning. Then in W_1 your first column will be the word embedding column vector for m, the second for because and so forth. The second option to extract word embeddings is to use each row of W_2 as the word embedding row vector for the corresponding word. Matrix W_2 has v rows, one row for each word in the vocabulary. Again, the order is the same as the input vector or matrix. So with our sample corpus and inputs, the first row would be the word embedding row vector for m, the second for because and so on. The third and final option is to take the average of the two previous representations. So if you want the word embedding column vectors, you would average W_1 and the transpose of W_2 to obtain W_3, a new n by v matrix. You can then extract the word embedding vectors from each column of W_3 as you did previously. So with our visual example, the word embedding for m would be the first column of W_3, which would be the average of the values of the first column of W_1 and of the first row of W_2. In this week's assignment, you'll be averaging W_1 transpose and W_2 to extracts the word embeddings as row vectors. Now that you know how to train these word vectors, in next week's video, you'll learn how to test them. Specifically, you will learn about two types of evaluation metrics. The first type is intrinsic evaluation and the second type is extrinsic evaluation.