Speech and Language Processing (3rd Edition) logo

Speech and Language Processing (3rd Edition)

Free

The NLP reference, kept current through the deep learning era (Jurafsky, Martin).

FreeFree tier
Type
Open Source

About Speech and Language Processing (3rd Edition)

A free online draft of the third edition of the definitive natural language processing textbook by Dan Jurafsky and James H. Martin. It covers the full spectrum of NLP and speech processing, from traditional methods to modern deep learning techniques including large language models, transformers, automatic speech recognition, text-to-speech, retrieval-augmented generation, and more. The draft is continuously updated with community feedback and is accompanied by lecture slides for educators.

Key Features

Free online draft of the complete textbook
Comprehensive coverage of NLP, computational linguistics, and speech recognition
Updated through the deep learning era with chapters on large language models, transformers, and post-training alignment
Includes automatic speech recognition and text-to-speech chapters
Accompanied by downloadable lecture slides in PPTX and PDF formats
Community-driven bug fixes and improvements incorporated into each release

Pros & Cons

Pros
  • Free to access, download, and use for educational purposes
  • Regular updates keep content current with fast-moving field
  • Broad and deep coverage, from fundamentals to state-of-the-art
  • Includes practical topics like information retrieval, RAG, and machine translation
  • Well-regarded by the NLP community and widely cited
Cons
  • Draft version may contain minor errors or missing references
  • Some chapters are still incomplete or in development
  • Only available as online PDF; no physical print edition yet
  • Large file size of the full book PDF may be cumbersome

Best For

Primary textbook for university NLP and speech processing coursesSelf-study resource for students and professionals entering the fieldReference guide for researchers and practitioners working on NLP systemsCurriculum development for educators teaching computational linguistics

FAQ

When will the book be finished?
The authors state 'Don't ask.' The third edition is a continuously updated draft, and new releases appear periodically.
How should I cite the book?
Use the following BibTeX entry: @Book{jm3, author = 'Daniel Jurafsky and James H. Martin', title = 'Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, with Language Models', year = '2026', url = {https://web.stanford.edu/~jurafsky/slp3/}, note = 'Online manuscript released January 6, 2026', edition = '3rd'}
Can I use the draft chapters in my class?
Yes, the authors encourage using the draft chapters and slides in classes, and they welcome feedback to improve the book.
How do I report typos or bugs?
Send comments to slp3edbugs@gmail.com and include the date of the draft.