CS 565: Intelligent Systems and Interfaces

Jan-May, 2016


Table of Contents

Syllabus and References

Event Date Description References
Introductory Lecture Jan 8 Course Introduction [ Lecture Slides ]
Lecture 1 Jan 13 Introduction to Natural Language Processing (NLP) [ Lecture Slides ]
[ Video lecture: Coursera Week 1- Introduction (part 1 and part 2) ]
[ Text Reference: Chapter 4 - 4.2, FSNLP ]
Lecture 2 Jan 20 Collocations [ Lecture Slides ] Updated on Jan 22
[ Text Reference: Chapter 5 - 5.2, FSNLP ]
Lecture 3 Jan 21 Finding Collocations (contd.) [ Lecture Slides ]
[ Text Reference: 5.3, FSNLP ]
Lecture 4 Jan 22 Finding Collocations: Alternative Tests [ Lecture Slides ]
[ Text Reference: 5.3 - 5.6, FSNLP ]
[ Prerequisite: Probability (Chapter 2, FSNLP), Maximum Likelihood Estimation (3 - 3.2, DHS) ]
Lecture 5 Jan 27 Project Guideline [ Project Guideline Slides ]
Lecture 6 Jan 28 Language Modeling [ Lecture Slides ]
[ Video lecture: Coursera Week 1 - The Language Modeling Problem ]
[ Text Reference: Chapter 'N-Grams' 6 - 6.2, SLP ]
Lecture 7 Feb 3 Estimating Parameters of N-gram models [ Lecture Slides ]
[ Video lecture: Coursera Week 1 - Parameter Estimation in Language Models ]
[ Prof. Collins Lecture Note ]
Reading Assignment Feb
4-5		 N-Grams,
Hidden Markov Models		 [ Chapters 'N-Grams' and 'Hidden Markov Models', SLP ]
Updated on Feb 9
Lecture 8 Feb 10 Sequence Labeling or Tagging Problems [ Lecture Slides ]
Lecture 9 Feb 11 Tagging Problems, and Hidden Markov Models (HMMs) [ Prof. Collins Lecture Note ]
[ Video lecture: Coursera Week 2 - Tagging Problems, and Hidden Markov Models ]
Optional Reading for HMMs:
Lecture 10 Feb 12 Log-linear Models [ Prof. Collins Lecture Note ]
[ Prof. Collins Lecture Slides: Coursera Week 7 - Log-linear Models: Introduction ]
Reading Assignment Feb
17-19		 Parameter Estimation in Log-linear Models [ Section 7, Prof. Collins Lecture Note ]
Lecture 11 Feb 25 Log-Linear Models for Tagging (MEMMs) [ Prof. Collins Lecture Slides ]
[ Video lecture: Coursera Week 8 - Log-linear Models for Tagging (MEMMs) ]
Relevant Lecture Notes :
Lectures
12-18		 Mar
9-11,
16, 19,
22, 24		 Introduction to Neural Networks [ Lecture Note ]
Lectures
19-20		 Mar
30-31		 Vector Semantics [ Lecture Slides ]
[ word2vec Explained: Negative Sampling Word Embedding ]
[ Neural Network Language Model: Video, Slides ]
[ Hierarchical Output layer: Video, Slides ]
[ Chapter 'Vector Semantics', SLP: Chapter, Slides ]

Text and Reference Book(s)

  1. FSNLP: Chris Manning and Hinrich Schütze. Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA: May 1999. Companion Website
  2. DHS: Duda, Richard O., Peter E. Hart, and David G. Stork. Pattern Classification. John Wiley & Sons, 2012. Companion Website
  3. SLP: Jurafsky, Dan, and James H. Martin. Speech and Language Processing. Pearson Education India, 2000. Companion Website

NLP Tools

  1. Five open source NLP tools: Link
  2. Tools for different NLP tasks: Link

Tutorials: NLP + Python

  1. Natural language Toolkit (NLTK) Tutorial: Book Set Up
  2. Python Numpy Tutorial: Stanford CS231n
  3. python-crfsuite Tutorial: Official Homepage
  4. Theano Tutorial: Speeding up your Neural Network with Theano and the GPU

Similar Courses

  1. Columbia University, Advanced NLP by Prof. Collins
  2. Stanford University, Deep Learning for Natural Language Processing
  3. Stanford University, Natural Language Understanding
  4. IIT Delhi, NLP by Dr. Mausam
  5. Stanford University, Convolutional Neural Networks for Visual Recognition

NLP Conference Calendar

Click here to access unofficially official conference calendar for the fields of Computational Linguistics and Natural Language Processing

© Ashish Anand, Web Development Advisor: Mohit Kumar, Web Developer: Saptarshi Pyne.