Chapter 1, Getting Started with Text Classification, introduces the reader to NLP and what a good NLP workflow looks like. You will also learn how to prepare text for machine learning with scikit-learn.
Chapter 2, Tidying Your Text, discusses some of the most common text pre-processing ideas. You will be introduced to spaCy and will learn how to use it for tokenization, sentence extraction, and lemmatization.
Chapter 3, Leveraging Linguistics, goes into a simple use case and examines how we can solve it. Then, we repeat this task again, but on a slightly different text corpus.
Chapter 4, Text Representations – Words to Numbers, introduces readers to the Gensim API. We will also learn to load pre-trained GloVe vectors and to use these vector representations instead of TD-IDF in any machine learning model.
Chapter 5, Modern Methods for Classification, looks at several new ideas regarding machine learning. The intention here is to demonstrate some of the most common classifiers. We will also learn about concepts such as sentiment analysis, simple classifiers, and how to optimize them for your datasets and ensemble methods.
Chapter 6, Deep Learning for NLP, cover what deep learning is, how it differs from what we have seen, and the key ideas in any deep learning model. We will also look at a few topics regarding PyTorch, how to tokenize text, and what recurrent networks are.
Chapter 7, Building Your Own Chatbot, explains why chatbots should be built and figures out the correct user intent. We will also learn in detail about intent , response, templates, and entities.
Chapter 8, Web Deployments, explains how to train a model and write some neater utils for data I/O. We are going to build a predict function and expose it using a Flask REST endpoint.
