Annie Louis: List of Tutorials

I update this page with NLP/ML tutorials, surveys and articles that I have read and found useful.

Some notes I have written

  1. Background for understanding Adaptor Grammars.

Interesting courses

Some courses at different universities that I think are exciting. Here are their reading lists.

  1. Bayesian Non-parametrics : University of Maryland, Spring 2013. Taught by Jordan Boyd-Graber, Hal Daume III and Naomi Feldman.
  2. Linguistic Prediction: Another unique course from University of Maryland (2014) looking at aspects of language prediction in the brain and computational models. Taught by Hal Daume III, Naomi Feldman and Ellen Lau.
  3. Algorithms for NLP: Taught at CMU by Alon Lavie, Chris Dyer, and Bob Frederking and previously by Noah Smith.
  4. History of Computational Linguistics: At Stanford (2011) by Dan Jurafsky.

Machine Learning and Background Math

  1. I've recently been finding Metacademy very useful in this regard. It tells you the background concepts for each technique and points to a variety of book, tutorial and video resources for any topic. Try it out [link]
  2. Jacob Eisenstein's reading list (many pointers to books)
  3. Generalized Linear Classifiers in NLP by Ryan McDonald.
  4. Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression chapter from Tom Mitchell's Machine Learning book.

Bayesian Inference

Some resources which helped me learn about Bayesian Inference.

  1. Christopher Bishop's talk at Machine Learning Summer School. The nuts and bolts to understand bayesian methods and graphical models in general.
  2. Shay Cohen's book (2016) Bayesian Analysis in Natural Language Processing
  3. A light-hearted and easy overview by Kevin Knight - Bayesian Inference with Tears
  4. Sharon Goldwater's reading list
  5. A list of papers using Bayesian methods compiled by students in Shay Cohen's class at Columbia Univ. Also see the readings for that class Bayesian analysis for NLP
  6. A reading list from University of Maryland's course on Bayesian Nonparametrics. Taught by Jordan Boyd-Graber, Hal Daume III and Naomi Feldman.

Topic models

  1. Video lecture and slides by David Blei at Machine Learning Summer School, 2009 at Cambridge UK. In fact, this summer school has a lot of other useful lectures, though I have not watched them all.
  2. An introductory tutorial by Mark Steyvers and Tom Griffiths.


  1. Automatic Summarization by Ani Nenkova and Kathy McKeown.
  2. A Statistical MT Workbook by Kevin Knight for intro/IBM models.