Course Information

This course gives an overview of modern data-driven techniques for natural language processing. The course moves from shallow bag-of-words models to richer structural representations of how words interact to create meaning. At each level, we will discuss the salient linguistic phenomena and most successful computational models. Along the way we will cover machine learning techniques which are especially relevant to natural language processing.

Slides, materials, and projects information for this iteration of NLP courses are borrowed from Jacob Eisenstein, Yulia Tsvetkov and Robert Frederking at CMU, Dan Jurafsky at Stanford, David Bamman at UC Berkeley, Noah Smith at UW, Kai-Wei Chang at UCLA.


Class Meets
Mondays and Wednesdays, 3:30-4:45pm
Staff Mailing List
Online Office Hours (Eastern Time)
Nihal Singh: Monday 2-3 pm.
Kaige Xie: Tuesday 6-7 pm.
Jingfeng Yang: Tuesday 10-11 pm.
Sandeep Soni: Wednesday 10-11 am.
Yuval Pinter: Thursday 10-11 am.
Haard Shah: Friday 2-3 pm.


Note: tentative schedule is subject to change.

Date Topic Optional Reading
Aug 17 Introduction, Review
Aug 19 Text Classification (1)
Aug 24 Text Classification (2)
Slides, HW1 Out, HW1 Template
Aug 26 Language Modeling (1)
Aug 31 Language Modeling (2)
Sep 2 Deep Learning Basics
Slides, Deep Leaning, Pytorch, HW2 Out, HW2 Template
HW1 Due.
Sep 7 Holiday - Labor Day
Sep 9 Word Embedding (1)
Sep 14 Word Embedding (2)
Survey Team Sign Up Due, Sign Up Form
Sep 16 Word Embedding (3)
Slides, HW3 Out, HW3 Template
HW2 Due
Sep 21 Sequence Labeling (1)
Sep 23 Sequence Labeling (2)
Sep 28 Constituency Parsing (1)
Sep 30 Constituency Parsing (2)
HW3 Due
Oct 5 In-person Touchpoint
HW4 Out, HW4 Code
Oct 7 Parsing
Survey Proposal Due
Oct 12 Midterm Review
Oct 14 Midterm
Oct 19 Question Answering
HW4 Due
Oct 21 Machine Translation
Slides, HW5 Out, HW5 Template, HW5 Code Template
Midterm Due
Oct 26 Alan Ritter's Guest Lecture:
Machine Reading with Less Supervision
Oct 28 Information Extraction
Nov 2 Dialogue Systems
Nov 4 Dialogue Systems + Review
HW5 Due
Nov 9 Computational Social Science
Nov 11 Xu Wei's Guest Lecture:
Natural Language Understanding for Noisy Text
Survey Report Due
Nov 16 Review
Nov 18 Computational Ethics


  • 55% Homework Assignments
    • Homework 1: 11%
    • Homework 2: 11%
    • Homework 3: 11%
    • Homework 4: 11%
    • Homework 5: 11%
  • 15% Midterm Exam (Take-home Exam)
  • 20% Project/Survey
    • Survey Proposal: Due Oct 7th, 11:59pm ET
    • Survey Report: Due Nov 11th, 11:59pm ET
    • Survey Final: Due Nov 22nd, 11:59pm ET
  • 10% Quiz


Late Policies:

Student will have a total of five late days to use when turning in homework assignments; each late day extends the deadline by 24 hours. There are no restrictions on how the late days can be used (e.g., all 5 could be used on one homework). Using late days will not affect your grade. However, homework submitted late after all late days have been used will receive no credit.

Class Policies:

Attendance will not be taken, but you are responsible for knowing what happens in every class. The instructor will try to post slides and notes online, and to share announcements, but there are no guarantees. So if you cannot attend class, make sure you check up with someone who was there.


The official prerequisite for CS 4650 is CS 3510/3511, “Design and Analysis of Algorithms.” This prerequisite is essential because understanding natural language processing algorithms requires familiarity with dynamic programming, as well as automata and formal language theory: finite-state and context-free languages, NP-completeness, etc. While course prerequisites are not enforced for graduate students, prior exposure to analysis of algorithms is very strongly recommended.

Furthermore, this course assumes:

  • Good coding ability, corresponding to at least a third or fourth-year undergraduate CS major. Assignments will be in Python.
  • Background in basic probability, linear algebra, and calculus.
  • Familiarity with machine learning is helpful but not assumed. Of particular relevance are linear classifiers: perceptron, naive Bayes, and logistic regression.

People sometimes want to take the course without having all of these prerequisites. Frequent cases are:

  • Junior CS students with strong programming skills but limited theoretical and mathematical background,
  • Non-CS students with strong mathematical background but limited programming experience.

Students in the first group suffer in the exam and don’t understand the lectures, and students in the second group suffer in the problem sets. My advice is to get the background material first, and then take this course.


  • The class is full. Can I still get in?

    Sorry. The course admins in CoC control this process. Please talk to them.

  • I am graduating this Fall and I need this class to complete my degree requirements. What should I do?

    Talk to the advisor or graduate coordinator for your academic program. They are keeping track of your degree requirements and will work with you if you need a specific course.

  • I have a question. What is the best way to reach the course staff?

    Registered students – your first point of contact is Piazza (so that other students may benefit from your questions and our answers). If you have a personal matter, email us at the class mailing list