Introduction to Transformer Models for NLP: Using BERT, GPT, and More to Solve Modern Natural Language Processing Tasks

Introduction to Transformer Models for NLP: Using BERT, GPT, and More to Solve Modern Natural Language Processing Tasks

by Sinan Ozdemir
Released August 2022
Publisher(s): Pearson
ISBN: 0137923716

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

10+ Hours of Video Instruction

Learn how to apply state-of-the-art transformer-based models including BERT and GPT to solve modern NLP tasks.

Overview
Introduction to Transformer Models for NLP LiveLessons provides a comprehensive overview of transformers and the mechanisms—attention, embedding, and tokenization—that set the stage for state-of-the-art NLP models like BERT and GPT to flourish. The focus for these lessons is providing a practical, comprehensive, and functional understanding of transformer architectures and how they are used to create modern NLP pipelines. Throughout this series, instructor Sinan Ozdemir will bring theory to life through illustrations, solved mathematical examples, and straightforward Python examples within Jupyter notebooks.

All lessons in the course are grounded by real-life case studies and hands-on code examples. After completing this lesson, you will be in a great position to understand and build cutting-edge NLP pipelines using transformers. You will also be provided with extensive resources and curriculum detail which can all be found at the course’s GitHub repository.

Ancillary files for this LiveLesson can be accessed at https://github.com/sinanuozdemir/oreilly-transformers-video-series.

About the Instructor
Sinan Ozdemir’is currently Founder and CTO of Shiba Technologies. Sinan is a former lecturer of Data Science at Johns Hopkins University and the author of multiple textbooks on data science and machine learning. Additionally, he is the founder of the recently acquired Kylie.ai, an enterprise-grade conversational AI platform with RPA capabilities. He holds a master’s degree in Pure Mathematics from Johns Hopkins University and is based in San Francisco, CA.

Skill Level
  • Intermediate
  • Advanced
Learn How To
  • Recognize which type of transformer-based model is best for a given task
  • Understand how transformers process text and make predictions
  • Fine-tune a transformer-based model
  • Create pipelines using fine-tuned models
  • Deploy fine-tuned models and use them in production
Who Should Take This Course
  • Intermediate/advanced machine learning engineers with experience with ML, neural networks, and NLP
  • Those interested in state-of-the art NLP architecture
  • Those interested in productionizing NLP models
  • Those comfortable using libraries like Tensorflow or PyTorch
  • Those comfortable with linear algebra and vector/matrix operations
Course Requirements
  • Python 3 proficiency with some experience working in interactive Python environments including Notebooks (Jupyter/Google Colab/Kaggle Kernels)
  • Comfortable using the Pandas library and either Tensorflow or PyTorch
  • Understanding of ML/deep learning fundamentals including train/test splits, loss/cost functions, and gradient descent
About Pearson Video Training:
Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Sams, and Que Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at http://www.informit.com/video.

Table of contents

  1. Introduction
    1. Introduction to Transformer Models for NLP: Introduction
  2. Lesson 1: Introduction to Attention and Language Models
    1. Topics
    2. 1.1 A brief history of NLP
    3. 1.2 Paying attention with attention
    4. 1.3 Encoder-decoder architectures
    5. 1.4 How language models look at text
  3. Lesson 2: How Transformers Use Attention to Process Text
    1. Topics
    2. 2.1 Introduction to transformers
    3. 2.2 Scaled dot product attention
    4. 2.3 Multi-headed attention
  4. Lesson 3: Transfer Learning
    1. Topics
    2. 3.1 Introduction to Transfer Learning
    3. 3.2 Introduction to PyTorch
    4. 3.3 Fine-tuning transformers with PyTorch
  5. Lesson 4: Natural Language Understanding with BERT
    1. Topics
    2. 4.1 Introduction to BERT
    3. 4.2 Wordpiece tokenization
    4. 4.3 The many embeddings of BERT
  6. Lesson 5: Pre-training and Fine-tuning BERT
    1. Topics
    2. 5.1 The Masked Language Modeling Task
    3. 5.2 The Next Sentence Prediction Task
    4. 5.3 Fine-tuning BERT to solve NLP tasks
  7. Lesson 6: Hands-on BERT
    1. Topics
    2. 6.1 Flavors of BERT
    3. 6.2 BERT for sequence classification
    4. 6.3 BERT for token classification
    5. 6.4 BERT for question/answering
  8. Lesson 7: Natural Language Generation with GPT
    1. Topics
    2. 7.1 Introduction to the GPT family
    3. 7.2 Masked multi-headed attention
    4. 7.3 Pre-training GPT
    5. 7.4 Few-shot learning
  9. Lesson 8: Hands-on GPT
    1. Topics
    2. 8.1 GPT for style completion
    3. 8.2 GPT for code dictation
  10. Lesson 9: Further Applications of BERT + GPT
    1. Topics
    2. 9.1 Siamese BERT-networks for semantic searching
    3. 9.2 Teaching GPT multiple tasks at once with prompt engineering
  11. Lesson 10: T5 – Back to Basics
    1. Topics
    2. 10.1 Encoders and decoders welcome: T5’s architecture
    3. 10.2 Cross-attention
  12. Lesson 11: Hands-on T5
    1. Topics
    2. 11.1 Off the shelf results with T5
    3. 11.2 Using T5 for abstractive summarization
  13. Lesson 12: The Vision Transformer
    1. Topics
    2. 12.1 Introduction to the Vision Transformer (ViT)
    3. 12.2 Fine-tuning an image captioning system
  14. Lesson 13: Deploying Transformer Models
    1. Topics
    2. 13.1 Introduction to MLOps
    3. 13.2 Sharing our models on HuggingFace
    4. 13.3 Deploying a fine-tuned BERT model using FastAPI
  15. Summary
    1. Introduction to Transformer Models for NLP: Summary

Product information

  • Title: Introduction to Transformer Models for NLP: Using BERT, GPT, and More to Solve Modern Natural Language Processing Tasks
  • Author(s): Sinan Ozdemir
  • Release date: August 2022
  • Publisher(s): Pearson
  • ISBN: 0137923716