You're reading from Transformers for Natural Language Processing Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI's GPT-3, ChatGPT, and GPT-4

Product type Paperback

Published in Mar 2022

Publisher Packt

ISBN-13 9781803247335

Length 602 pages

Edition 2nd Edition

Languages

Processing

Tools

Processing

Concepts

Mobile Application Development

Author (1):

Denis Rothman

View More author details

Table of Contents (25) Chapters

Preface

1. What are Transformers? FREE CHAPTER

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

Explainable AI (XAI)

You can add XAI to your programs if you are interested in implementing advanced prompt engineering with OpenAI’s state-of-the-art models that can explain outputs. ChatGPT can explain source code. It can also explain its own outputs to a certain extent.

We went through some of the main aspects of explainable AI in Chapter 14, Interpreting Black Box Transformer Models.

To go further, you can try using ChatGPT to explain ChatGPT outputs and other tools by running XAI_by_ChatGPT_for_ChatGPT.ipynb, which is in the Bonus directory of the GitHub repository of this book. The program runs a ChatGPT XAI analysis of a ChatGPT output and also shows how to explain outputs with SHAP.

The notebook is self-contained and can help you, the advanced reader, build XAI on top of the tools in this notebook.

Let’s add audio to our dialogue with ChatGPT.

Speech-to-text with Whisper

In this section, we will run a speech-to-text model...

The rest of the chapter is locked

You're reading from Transformers for Natural Language Processing Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI's GPT-3, ChatGPT, and GPT-4

Table of Contents (25) Chapters

Explainable AI (XAI)

Speech-to-text with Whisper

Unlock this book and the full library FREE for 7 days

Authors (1)