Convert movie-review string data to a sparse feature vector. Implement a sentiment-analysis linear model using a sparse feature vector. Implement a sentiment-analysis DNN model using an embedding that projects data into two dimensions. Visualize the embedding to see what the model has learned about the relationships between words. In this exercise, we'll explore sparse data and work with embeddings using text data from movie reviews (from the ACL 2011 IMDB dataset). This data has already been processed into tf.Example format.