Courses and tutorials

Here are some good tutorials, demonstrations, and even courseware from renowned university programs, many of which include Python examples:

• Speech and Language Processing (https://web.stanford.edu/~jurafsky/slp3/ed3book.pdf) by David Jurafsky and James H. Martin—The next book you should read if you’re serious about NLP. Jurafsky and Martin are more thorough and rigorous in their explanation of NLP concepts. They have whole chapters on topics that we largely ignore, like finite state transducers (FSTs), hidden Markhov models (HMMs), part-of-speech (POS) tagging, syntactic parsing, discourse coherence, machine translation, summarization, and dialog systems.
• MIT Artificial General Intelligence course 6.S099 (https://agi.mit.edu) led by Lex Fridman Feb 2018—MIT’s free, interactive (public competition!) AGI course. It’s probably the most thorough and rigorous free course on artificial intelligence engineering you can find.
• Textacy: NLP, before and after spaCy (https://github.com/chartbeat-labs/textacy)—Topic modeling wrapper for SpaCy.
• MIT Natural Language and the Computer Representation of Knowledge course 6-863j lecture notes (http://mng.bz/vOdM) for Spring 2003.
• Singular value decomposition (SVD) (http://people.revoledu.com/kardi/tutorial/LinearAlgebra/SVD.html) by Kardi Teknomo, PhD.
• An Introduction to Information Retrieval (https://nlp.stanford.edu/IR-book/pdf/irbookonlinereading.pdf) by Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze.