Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Mastering Transformers

You're reading from  Mastering Transformers

Product type Book
Published in Sep 2021
Publisher Packt
ISBN-13 9781801077651
Pages 374 pages
Edition 1st Edition
Languages
Authors (2):
Savaş Yıldırım Savaş Yıldırım
Profile icon Savaş Yıldırım
Meysam Asgari- Chenaghlu Meysam Asgari- Chenaghlu
Profile icon Meysam Asgari- Chenaghlu
View More author details

Table of Contents (16) Chapters

Preface 1. Section 1: Introduction – Recent Developments in the Field, Installations, and Hello World Applications
2. Chapter 1: From Bag-of-Words to the Transformer 3. Chapter 2: A Hands-On Introduction to the Subject 4. Section 2: Transformer Models – From Autoencoding to Autoregressive Models
5. Chapter 3: Autoencoding Language Models 6. Chapter 4:Autoregressive and Other Language Models 7. Chapter 5: Fine-Tuning Language Models for Text Classification 8. Chapter 6: Fine-Tuning Language Models for Token Classification 9. Chapter 7: Text Representation 10. Section 3: Advanced Topics
11. Chapter 8: Working with Efficient Transformers 12. Chapter 9:Cross-Lingual and Multilingual Language Modeling 13. Chapter 10: Serving Transformer Models 14. Chapter 11: Attention Visualization and Experiment Tracking 15. Other Books You May Enjoy

Working with tokenization algorithms

In the opening part of the chapter, we trained the BERT model using a specific tokenizer, namely BertWordPieceTokenizer. Now it is worth discussing the tokenization process in detail here. Tokenization is a way of splitting textual input into tokens and assigning an identifier to each token before feeding the neural network architecture. The most intuitive way is to split the sequence into smaller chunks in terms of space. However, such approaches do not meet the requirement of some languages, such as Japanese, and also may lead to huge vocabulary problems. Almost all Transformer models leverage subword tokenization not only for reducing dimensionality but also for encoding rare (or unknown) words not seen in training. The tokenization relies on the idea that every word, including rare words or unknown words, can be decomposed into meaningful smaller chunks that are widely seen symbols in the training corpus.

Some traditional tokenizers developed...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime}