CS 4705: Introduction to Natural Language Processing, Fall 2017

Course Information
Time TTh: 2:40-3:55pm Place 501 Northwest Corner
Professor Kathleen McKeown Office Hours Tu 4:00-5:00,We 4-5, 722 CEPSR
Email kathy@cs.columbia.edu Phone 212-939-7114
Teaching Assistants
Elsbeth Turcan Office Hours Tues 11:00-1:00 CEPSR 7LW1 (NLP Lab)
Dheeraj Kalmekolan Office Hours Sat 4-5 (CVN only), Sun 2-3 (in-person) Google Hangouts, Mudd 122 (TA Room)
Apoorv Kulshreshtha Office Hours Thurs 4:00-6:00 Mudd 122 (TA Room)
Robert Kwiatkowski Office Hours Thurs 12:30-2:30 Mudd 122 (TA Room)
Fei-Tzin Lee Office Hours Mon 4:00-6:00 CEPSR 7LW1 (NLP Lab)
Bhavana Ramachandra Office Hours Mon and Wed 11:00-1:00 Mudd 122 (TA Room)
Samarth Tripathi Office Hours Fri 4:00-6:00 Mudd 122 (TA Room)

Course Description

This course provides an introduction to the field of natural language processing (NLP). We will learn how to create systems that can analyze, understand and produce language. We will begin by discussing core NLP, such as language modeling, part of speech tagging and parsing. We will also discuss applications such as information extraction, machine translation, automatic summarization, and question-answering. The course will primarily cover statistical and machine learning based approaches to language processing, but it will also introduce the use of linguistic concepts that play a role. We will study machine learning methods currently used in NLP, including supervised machine learning, hidden markov models, and neural networks. Homework assignments will include both written components and programming assignments.


Four homework assignments, a midterm and a final exam. Each student in the course is allowed a total of 4 late days on homeworks with no questions asked; after that, 10% per late day will be deducted from the homework grade, unless you have a note from your doctor. Do not use these up early! Save them for real emergencies.

We will use Google Cloud for the course. Instructions for setting up the cloud can be found here.


Speech and Language Processing, 2nd Edition, by Jurafsky and Martin. It will be available from Book Culture, as well as from Amazon and other online providers. It should also be on reserve in the Engineering Library.

Neural Network Methods for Natural Language Processing by Yoav Goldberg. It is available online but you can also purchase hard copy from the publisher.


This syllabus is still subject to change. Readings may change. But it will give you a good idea of what we will cover.

Week Class Topic Reading Assignments
1 Sep 5 Introduction and Course Overview Ch 1, Speech and Language
Sep 7 Language modeling Ch 4, Speech and Language HW0: setup. Required python code
2 Sep 12 Supervised machine learning, text classification Ch 2 Neural Nets, HW0 due (Submit before 2:40pm). HW1: Republican or Democrat?: training data development data training data with new lines development data with new lines
Sep 14 Supervised machine learning, Scikit Learn Tutorial
3 Sep 19 POS tagging C 5.1-5.5 Speech and Language
Sep 21 Methods: Hidden Markov Modeling C 6.1-6.5, Speech and Language
4 Sep 26 Syntax and Grammars C 12 Speech and Language HW1 due
Sep 28 Parsing C. 13 Speech and Language, HW2: Parsing
Required Code
5 Oct 3 Dependency Parsing C 14.6 Speech and Language; Dependency Parsing, C. 3 (Courseworks)
Oct 5 Dependency Parsing, Evaluation C 14, Speech and Language
6 Oct 10 Introduction to Semantics C 17 Speech and Language
Oct 12 Lexical Semantics, Word Sense Disambuation C 19, C 20.1-20.8 Speech and Language Sample Midterm Questions Sample Midterm Questions and Answers HW 2 due
(Saturday, Oct. 14, 2 PM)
7 Oct 17 Word Sense Disambuation and Midterm Review C 20.9
Oct 19 Midterm
8 Oct 24 Semantic Parsing References on slides
Oct 26 Word Embeddings C 10, 3,4,5,10 Neural Nets
9 Oct 31 Neural Nets C 3,4,5 Neural Nets HW3: Neural Nets
PrerequisitesHW3 Assignment
Nov 2 Text Similarity C 11 Neural Nets
10 Nov 9 Sentiment Analysis and RNNs C 14, 15.1,15.2, 16.1 Neural Nets
11 Nov 14 Summarization papers HW 3 due by 2:30pm
Nov 16 Summarization C 23.5 - 23.8 Speech and Language, Abstractive Neural net approach HW 4
12 Nov 21 Summarization Exractive Neural Net Approach
Nov 23 Thanksgiving
13 Nov 28 Machine Translation Speech and Language, C 25
Nov 30 Neural Machine Translation Neural Nets, C. 17.4, 17.5.1
14 Dec 5 Information Extraction Speech and Language, C 22.1-22.2
Dec 7 Poetry and Review Poetry and Review Papers HW 4 due EXTENDED: NOW DUE DEC. 11th at NOON


Check Piazza for announcements, your grades (only you will see them), and discussion. All questions should be posted through Piazza instead of emailing Professor McKeown or the TAs. They will monitor the discussion lists to answer questions.

Academic Integrity

Copying or paraphrasing someone's work (code included), or permitting your own work to be copied or paraphrased, even if only in part, is not allowed, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you believe you are going to have trouble completing an assignment, please talk to the instructor or TA in advance of the due date