Summary
NLP is a very exciting topic. It's also a difficult one because of the complexity of language in general, and due to how much processing is required to build datasets. Having said that, the built-in algorithms in SageMaker will help you get good results out of the box. Training and deploying models are straightforward processes, which leaves you more time to explore, understand, and prepare data.
In this chapter, you learned about the BlazingText, LDA, and NTM algorithms. You also learned how to process datasets using popular open source tools such as nltk, spacy, and gensim, and how to save them in the appropriate format. Finally, you learned how to use the SageMaker SDK to train and deploy models with all three algorithms, as well as how to interpret the results. This concludes our exploration of built-in algorithms.
In the next chapter, you will learn how to use built-in machine learning frameworks such as scikit-learn, TensorFlow, PyTorch, and Apache MXNet.
...
