You're reading from Transformers for Natural Language Processing - Second Edition

Product type Book

Published in Mar 2022

Publisher Packt

ISBN-13 9781803247335

Pages 602 pages

Edition 2nd Edition

Languages

Concepts

Mobile Application Development

Author (1):

Denis Rothman

Table of Contents (25) Chapters

Preface

1. What are Transformers?

2. Getting Started with the Architecture of the Transformer Model

3. Fine-Tuning BERT Models

4. Pretraining a RoBERTa Model from Scratch

5. Downstream NLP Tasks with Transformers

6. Machine Translation with the Transformer

7. The Rise of Suprahuman Transformers with GPT-3 Engines

8. Applying Transformers to Legal and Financial Documents for AI Text Summarization

9. Matching Tokenizers and Datasets

10. Semantic Role Labeling with BERT-Based Transformers

11. Let Your Data Do the Talking: Story, Questions, and Answers

12. Detecting Customer Emotions to Make Predictions

13. Analyzing Fake News with Transformers

14. Interpreting Black Box Transformer Models

15. From NLP to Task-Agnostic Transformer Models

16. The Emergence of Transformer-Driven Copilots

17. The Consolidation of Suprahuman Transformers with OpenAI’s ChatGPT and GPT-4

18. Other Books You May Enjoy

19. Index

Appendix I — Terminology of Transformer Models

1. Appendix II — Hardware Constraints for Transformer Models

2. Appendix III — Generic Text Completion with GPT-2

3. Appendix IV — Custom Text Completion with GPT-2

4. Appendix V — Answers to the Questions

Summary

In this chapter, we discovered the new era of transformer models training billions of parameters on supercomputers. OpenAI’s GPT models are taking NLU beyond the reach of most NLP development teams.

We saw how a GPT-3 zero-shot model performs many NLP tasks through an API and even directly online without an API. The online version of Google Translate has already paved the way for mainstream online usage of AI.

We explored the design of GPT models, which are all built on the original transformer’s decoder stack. The masked attention sub-layer continues the philosophy of left-to-right training. However, the sheer power of the calculations and the subsequent self-attention sub-layer makes it highly efficient.

We then implemented a 345M parameter GPT-2 model with TensorFlow. The goal was to interact with a trained model to see how far we could get with it. We saw that the context provided conditioned the outputs. However, it did not reach the results...