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

Training a text classifier in Flair

In this section, we will be training a sentiment analysis text classification model capable of labeling text as positive or negative. Text classifier training follows a sequence of steps very similar to how sequence labeling models are trained.

The steps required to train text classifiers in Flair include the following:

  1. Loading a tagged corpus and computing the label dictionary map
  2. Loading and preparing the document embeddings
  3. Initializing the TextClassifier class
  4. Training the model

The process, given what we covered as part of sequence labeling model training, should look very familiar – and indeed it is. Let's start by loading the data required to train the classifier.

Loading a tagged corpus

Training text classification models requires a set of text documents (typically, sentences or paragraphs) where each document is associated with one or more classification labels. To train our sentiment analysis...