Helion


Szczegóły ebooka

Natural Language Processing with Flair

Natural Language Processing with Flair

Tadej Magajna

Kup pozycję na ebookpoint.pl

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.

  • Natural Language Processing with Flair
  • Contributors
  • About the author
  • About the reviewers
  • Preface
    • Who this book is for
    • What this book covers
    • To get the most out of this book
    • Download the example code files
    • Download the color images
    • Conventions used
    • Get in touch
    • Share Your Thoughts
  • Part 1: Understanding and Solving NLP with Flair
  • Chapter 1: Introduction to Flair
    • Technical requirements
    • A brief introduction to NLP
      • Tokenization
      • Text vectorization
      • Named entity recognition
      • Word-sense disambiguation
      • Part-of-speech tagging
      • Chunking
      • Stemming and lemmatization
      • Text classification
    • Introducing Flair
    • Setting up the development environment
      • Creating the virtual environment
      • Installing a published version of Flair in a virtual environment
      • Installing directly from the GitHub repository (optional)
      • Running code that uses Flair
    • Summary
  • Chapter 2: Flair Base Types
    • Technical requirements
    • Sentence and Token objects
      • Understanding the Sentence class
      • Understanding the Token class
      • Tokenization in Flair
      • Sentence and Token object helper methods
    • Using custom tokenizers
      • Using the TokenizerWrapper class
    • Understanding the Corpus object
    • Summary
  • Chapter 3: Embeddings in Flair
    • Technical requirements
    • Understanding word embeddings
      • Cosine similarity
      • The "king man queen woman" analogy
    • Classic word embeddings in Flair
    • Flair embeddings
      • Understanding the contextuality of Flair embeddings
      • Character-level sequence modeling in Flair embeddings
      • Pooled Flair embeddings
      • Available Flair embeddings
    • Stacked embeddings
    • Document embeddings
    • Other embeddings in Flair
    • Summary
  • Chapter 4: Sequence Tagging
    • Technical requirements
    • Understanding sequence tagging in Flair
    • Named entity recognition in Flair
      • Types of NER taggers in Flair
    • Part-of-speech tagging in Flair
      • Part-of-speech tagging tag sets
      • Types of PoS taggers in Flair
      • Other tagging tasks in Flair
    • Sequence labeling metrics
      • Measuring accuracy for sequence labeling tasks
      • Measuring the F1 score for sequence labeling tasks
    • Summary
  • Part 2: Deep Dive into Flair Training Custom Models
  • Chapter 5: Training Sequence Labeling Models
    • Technical requirements
    • The motivation behind training custom models
    • Understanding the hardware requirements for training models
    • Working with parameters for training and evaluation
      • Understanding neural model training
      • Parameters and terminology used in Flair model training
    • Training custom sequence labeling models
      • Loading a tagged corpus
      • Loading the tag dictionary
      • Building the embedding stack
      • Initializing the SequenceTagger object
      • Training the model
      • Understanding training output files
      • Loading and using custom Flair models
    • Knowing when to stop and try again
      • Monitoring loss
      • Assessing and comparing performance metrics
    • Summary
  • Chapter 6: Hyperparameter Optimization in Flair
    • Technical requirements
    • Understanding hyperparameter tuning
      • Optimization methods
    • Hyperparameter tuning in Python
      • Hyperparameter tuning in Python hands-on
    • Hyperparameter optimization in Flair
      • Hyperparameter tuning in Flair hands-on
    • Summary
  • Chapter 7: Train Your Own Embeddings
    • Technical requirements
    • Understanding the how and why behind custom Flair embeddings
      • Why training embeddings rarely ever means training embeddings
      • Corpora for Flair embeddings
      • Dictionaries for training Flair embeddings
    • Evaluating word embeddings
    • Training Flair embeddings on the worlds smallest language
      • Preparing the dictionary
      • Preparing the corpus
      • Training the language model
      • Using custom embeddings on downstream tasks
      • Performing intrinsic evaluation on custom Flair embeddings
    • Summary
  • Chapter 8: Text Classification in Flair
    • Technical requirements
    • Understanding text classification
      • Training text classifiers
    • Text classification in Flair
      • Using pre-trained Flair text classification models
      • Document embeddings in Flair
      • Text classifiers in Flair
    • Training a text classifier in Flair
    • Working with text classifiers that require little to no training data
      • Zero-shot classification with TARS
      • Few-shot classification with TARS
    • Summary
  • Part 3: Real-World Applications with Flair
  • Chapter 9: Deploying and Using Models in Production
    • Technical requirements
    • Technical considerations for NLP models in production
      • Client-side versus server-side inference
      • When to use managed services and when to self-serve server-side models
      • Managed services for Flair models
      • A model deployment decision-making flowchart
    • Self-serving flair models
      • A proof-of-concept self-serve tool for Flair
    • Using managed services for deploying and using Flair models
      • The Hugging Face Models Hub
    • Summary
  • Chapter 10: Hands-On Exercise Building a Trading Bot with Flair
    • Technical requirements
    • Understanding the trading strategy
    • Implementing the Flair trading bot
    • A Flair coding cheat sheet
    • Summary
    • Why subscribe?
  • Other Books You May Enjoy
    • Packt is searching for authors like you
    • Share Your Thoughts