TIL Jurafsky & Martin, the textbook I used for Computational Linguistics in undergrad many years ago (when TAU didn’t offer that class), released a second edition in 2026, and it has one of the clearest explanations of Transformers I have seen to date.

https://t.co/FyCukgQTtb https://t.co/ZKCYSevjas

Speech and Language Processing

Source: https://web.stanford.edu/~jurafsky/slp3/

Speech and Language Processing(3rd ed. draft) Dan JurafskyandJames H. Martin

Here’s our Jan 6, 2026 release!

This release has is mainly a cleanup and bug-fixing release, with some updated figures for the transformer in various chapters. The August release made larger changes, including DPO in chapter 9, new ASR and TTS chapters, a restructured LLM chapter, and unicode in Chapter 2. Individual chapters and updated slides are below.

Here is a single pdf of Jan 6, 2026 book!

1. Feel free to use the draft chapters and slides in your classes, print it out, whatever, the resulting feedback we get from you makes the book better!
2. Typos and commentsare very welcome (just email[email protected]and let us know the date on the draft)! (Don’t bother reporting missing refs due to cross-chapter cross-reference problems in the indvidual chapter pdfs, those are fixed in the full book draft)
3. **Gratitude!**We’ve put up alist hereof the amazing people who have sent so many fantastic suggestions and bug-fixes for improving the book. We are really grateful to all of you for your help, the book would not be possible without you!
4. How to cite the book:Daniel Jurafsky and James H. Martin. 2026. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition. Online manuscript released January 6, 2026. https://web.stanford.edu/~jurafsky/slp3.
5. Abib entryfor the book ishere.@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", }
6. Whenwill the book be finished? Don’t ask.
7. If you need the previous Aug 2025 draft chapters, they arehere; if you need the previous Jan 2025 draft chapters, they arehere;

Volume I: Large Language ModelsChapterSlides1:Introduction2:Words and Tokens2: Words and Tokens [pptx] [pdf] 2: Edit Distance [pptx] [pdf] 3:N-gram Language Models3: [pptx] [pdf] 4:Logistic Regression and Text Classification4: [pptx] [pdf] 5:Embeddings5: [pptx] [pdf]6:Neural Networks6: [pptx] [pdf]7:Large Language Models7: [pptx] [pdf]8:Transformers8: [pptx] [pdf] 9:Post-training: Instruction Tuning, Alignment, and Test-Time Compute10:Masked Language Models10: [pptx] [pdf]11:Information Retrieval and Retrieval-Augmented Generation11: [pptx] [pdf]12:Machine Translation13:RNNs and LSTMs13: [pptx] [pdf]14:Phonetics and Speech Feature Extraction15:Automatic Speech Recognition16:Text-to-SpeechVolume II: Annotating Linguistic StructureChapterSlides17:Sequence Labeling for Parts of Speech and Named Entities17: (Intro only) [pptx] [pdf]18:Context-Free Grammars and Constituency Parsing19:Dependency Parsing20:Information Extraction: Relations, Events, and Time21:Semantic Role Labeling and Argument Structure22:Lexicons for Sentiment, Affect, and Connotation23:Coreference Resolution and Entity Linking24:Discourse Coherence25:Conversation and its Structure**Appendix (will be just on the web)**A:Hidden Markov ModelsB:Naive Bayes ClassificationB: [pptx] [pdf] C:Kneser-Ney SmoothingD:Spelling Correction and the Noisy ChannelE:Statistical Constituency ParsingF:Context-Free GrammarsG:Combinatory Categorial GrammarH:Logical Representations of Sentence MeaningI:Word Senses and WordNetJ:PPMIK:Frame-based Dialogue Systems