Hands-On Deep Learning with R

Summary

In this chapter, we covered a number of methods for analyzing text data. We started with techniques for extracting elements from text data, such as taking a sentence and breaking it into tokens and comparing term frequency, along with collecting topics and identifying the best summary sentence and extracting these from the text. Next, we used some embedding techniques to add additional details to our data, such as parts of speech and named entity recognition. Lastly, we used an RBM model to find latent features in the input data and stacked these RBM models to perform a classification task. In the next chapter, we will look at using deep learning for time series tasks, such as predicting stock prices, in particular.