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

Named entity recognition in Flair

NER is a special sequence tagging task that identifies and labels named entities. Named entities are real-word objects such as persons, locations, or organizations. The set of possible distinct named entities isn't strictly defined and may vary from model to model. Flair ships with a rich set of pretrained NER models, as well as tools to train custom models. In this section, we are going to focus on covering the pretrained models, as well as how to interpret and understand their output.

To get a good understanding of how NER tagging works in Flair, let's try it out as part of an exercise. We will start with tagging a single word that is clearly a named entity.

from flair.data import Sentence
from flair.models import SequenceTagger
tagger = SequenceTagger.load('ner')
sentence = Sentence('Berlin')
tagger.predict(sentence)
print(sentence.to_tagged_string())

In the preceding script, we loaded Flair's default...