Speech and Language Processing — Jurafsky & Martin

Daniel Jurafsky & James H. Martin, 3rd Edition (draft)

The core NLP textbook: tokens, n-grams, classification, embeddings, neural networks, RNNs, transformers, LLMs, post-training, masked LMs, information retrieval, RAG, machine translation, speech, sequence labeling, parsing, information extraction, coreference, and conversation. Primary textbook for Course 3.

Chapters

Exercises added as I work through each chapter.