Chapter 1, Introducing FastText, introduces fastText and the NLP context in which this library is useful. It will map the motivations behind building the library and the intended usage and benefits that the creators of the library intended to bring into NLP and the field of computational linguistics. There will also be specific instructions explaining how to install fastText on your work machine. Upon completion of this chapter, you will have fastText installed and running on your computer.
Chapter 2, Creating Models Using the FastText Command Line, discusses the rich command line that the fastText library provides. This chapter describes the default command-line options and shows how to use it to create models. If you are only interested in having a superficial introduction to fastText, reading up to this chapter should be enough.
Chapter 3, Word Representations in FastText, explains how unsupervised word embeddings are created in fastText.
Chapter 4, Sentence Classification in FastText, introduces the algorithms that power sentence classification in fastText. You will also learn how fastText compresses big models into smaller models that can be deployed to low-memory devices.
Chapter 5, FastText in Python, is about creating models in Python by either using the official Python bindings for fastText or by using the gensim library, which is a popular Python library for NLP.
Chapter 6, Machine Learning and Deep Learning Models, explains how to integrate fastText into your NLP pipeline if you have pre-built pipelines that use either statistical machine learning paradigms or deep learning paradigms. In the case of statistical machine learning, this chapter makes use of the scikit-learn library; and in the case of deep learning, Keras, TensorFlow, and PyTorch are taken into account.
Chapter 7, Deploying Models to Mobile and the Web, is mainly about deployment and how to integrate fastText models in live production-grade customer applications.
