Book Image

Natural Language Processing with Flair

By : Tadej Magajna
Book Image

Natural Language Processing with Flair

By: Tadej Magajna

Overview of this book

Flair is an easy-to-understand natural language processing (NLP) framework designed to facilitate training and distribution of state-of-the-art NLP models for named entity recognition, part-of-speech tagging, and text classification. Flair is also a text embedding library for combining different types of embeddings, such as document embeddings, Transformer embeddings, and the proposed Flair embeddings. Natural Language Processing with Flair takes a hands-on approach to explaining and solving real-world NLP problems. You'll begin by installing Flair and learning about the basic NLP concepts and terminology. You will explore Flair's extensive features, such as sequence tagging, text classification, and word embeddings, through practical exercises. As you advance, you will train your own sequence labeling and text classification models and learn how to use hyperparameter tuning in order to choose the right training parameters. You will learn about the idea behind one-shot and few-shot learning through a novel text classification technique TARS. Finally, you will solve several real-world NLP problems through hands-on exercises, as well as learn how to deploy Flair models to production. By the end of this Flair book, you'll have developed a thorough understanding of typical NLP problems and you’ll be able to solve them with Flair.
Table of Contents (15 chapters)
1
Part 1: Understanding and Solving NLP with Flair
6
Part 2: Deep Dive into Flair – Training Custom Models
11
Part 3: Real-World Applications with Flair

Hyperparameter tuning in Python

Let's get a taste of what hyperparameter tuning looks like in practice. We will use one of the most popular Python hyperparameter optimization libraries called Hyperopt. First, let's get a general idea of how to use it in practice.

Hyperopt is a Python library that provides an easy-to-use API that requires the following three objects:

  • A search space
  • An objective function
  • An optimization method

Let's look at each of these requirements in detail:

  • Search space is simply the space within which the optimizer will search for different hyperparameter options. The library provides the following parameter expressions:
    • Categorical parameters – Parameter values that are purely categorical and can even be non-scalar (they do not need to be a number). They are provided via the hyperopt.hp.choice method.
    • Integer parameters – Integer value parameters obtained via methods such as hyperopt.hp.quniform or hyperopt...