Natural Language Processing:
Neural Networks and Large Language Models

https://github.com/NiuTrans/NLPBook

https://niutrans.github.io/NLPBook

Tong Xiao and Jingbo Zhu

This is a book on neural networks and large language models in NLP. It is intended for anyone interested in NLP and deep learning. Some of the chapters are drawn from our previously published articles (e.g., Introduction to Transformers: An NLP Perspective and Foundations of Large Language Models), but we have added significant new content.

Chapters

• Table of Contents [pdf]
• Part I: Preliminaries
  • Chapter 1: Foundations of Machine Learning [pdf]
  • Chapter 2: Foundations of Neural Networks [pdf]
• Part II: Basic Models
  • Chapter 3: Words and Word Vectors [pdf]
  • Chapter 4: Recurrent and Convolutional Sequence Models [pdf]
  • Chapter 5: Sequence-to-Sequence Models [pdf]
  • Chapter 6: Transformers [pdf]
• Part III: Large Language Models
  • Chapter 7: Pre-training [pdf]
  • Chapter 8: Generative Models [pdf]
  • Chapter 9: Prompting [pdf]
  • Chapter 10: Alignment [pdf]
  • Chapter 11: Inference [pdf]
  • Chapter 12: Reasoning [pdf] 🆕

Here's the complete version containing all the chapters [pdf].

Citing This Book

@book{Xiao-and-Zhu:2025NLP,
  title={Natural Language Processing: Neural Networks and Large Language Models},
  author={Tong Xiao and Jingbo Zhu},
  publisher={NiuTrans},
  year={2025}
}

Translations of This Book

This book has been translated into multiple languages using LLMs. You can find these translations at https://github.com/NiuTrans/NLPBookTranslations. The available languages include Chinese, Japanese, French, German, Italian and Portuguese.

Contact Us

For any issues or comments, please feel free to contact the authors directly via e-mail: xiaotong [at] mail.neu.edu.cn