Natural Language Processing

11-411 for undergrads | 11-611 for grads

Overview

Syllabus
Lecture
Section A: Tuesdays and Thursdays, 3:00-4:20pm (GHC 4307)
Section B: Video Section
Instructors
Office Hours by appointment
Teaching Assistants
TA Office Hours
(Location: GHC 5th Floor, LTI common area)
Textbook
Speech and Language Processing (2nd Edition, 2007, Prentice-Hall), by Daniel Jurafsky and James Martin
Cheating Policy
Resources

Course Description

This course is about a variety of ways to represent human languages (like English and Chinese) as computational systems, and how to exploit those representations to write programs that do neat stuff with text and speech data, like

This field is called Natural Language Processing or Computational Linguistics, and it is extremely multidisciplinary. This course will therefore include some ideas central to Machine Learning and to Linguistics.

We'll cover computational treatments of words, sounds, sentences, meanings, and conversations. We'll see how probabilities and real-world text data can help. We'll see how different levels interact in state-of-the-art approaches to applications like translation and information extraction.

From a software engineering perspective, there will be an emphasis on rapid prototyping, a useful skill in many other areas of Computer Science.

Course Prerequisites

CS courses on data structures and algorithms, and strong programming skills.

Schedule

# Date Topic Readings Assignments and
Project milestones
1 Jan 15 Course overview; What does it mean to know language?
Slides
Lecture Video
Chap 1
2 Jan 17 Information extraction, question answering, and NLP in IR
Slides
Lecture Video
Chap 22.0-2, 23.0-2
3 Jan 22 Project
Slides
Lecture Video / Lecture Video (better audio)
4 Jan 24 Words, morphology, and lexicons
Slides
Lecture Video
Chap 3.1-3.9 Assignment 1 out
5 Jan 29 Language models and smoothing
Slides
Lecture Video
Chap 4.3-8
Jan 31 Class is canceled. Assignment 1 due
Assignment 2 out
6 Feb 5 Noisy channel models and edit distance
Slides
Lecture Video
Chap 3.10, 3.11, 5.9
7 Feb 7 Classification
Slides
Lecture Video
Assignment 2 due
Assignment 3 out
8 Feb 12 Part of speech tags
Slides
Lecture Video
Chap 5.0-3
9 Feb 14 Hidden Markov models
Slides
Lecture Video
Chap 6.0-4 Assignment 3 due
Assignment 4 out
10 Feb 19 Syntactic representations of natural language
Slides
Lecture Video
Chap 12.0-3
11 Feb 21 Chomsky hierarchy and natural language
Slides
Lecture Video
Chap 15
12 Feb 26 Context-free recognition, CKY
Slide1
Slide2
Lecture Video
13 Feb 28 Parsing algorithms
Slides
Lecture Video
Chap 12.7, Chap 13, Chap 14-14.2 Assignment 4 due
Assignment 5 out
14 Mar 5 Treebanks and PCFGs
Slides
Lecture Video
Chap 12.4, 14.7 Project Progress Report due 11:59pm
Mar 7 Midterm exam
15 Mar 19 Lexical semantics
Slides
Lecture Video
Chap 17.0-2, 19.0-3
16 Mar 21 Word embeddings/vector semantics
Slides
Lecture Video
SLP3 Chap 6 Assignment 5 due
Assignment 6 out
17 Mar 26 Verb/sentence semantics
Slides A
Slides B
Lecture Video
Chap 17.2-4, Chap 19.4-6
18 Mar 28 Compositional semantics, semantic parsing
Slides
Lecture Video
Chap 18.1-3
19 Apr 2 Word Sense Disambiguation and Semantic Role Labelling
Slides
Lecture Video
Chap 20
20 Apr 4 Discourse, entity linking, pragmatics
Slides
Lecture Video
Chap 20.0-6, 20.8-11 Assignment 6 due
Assignment 7 out
21 Apr 9 Speech 1
Slides
Lecture Video
Project dry run code due 11:59 PM
22 Apr 16 Speech 2
Slides
Lecture Video
23 Apr 18 Non-English NLP
Slides
Lecture Video
Assignment 7 due
24 Apr 23 Interpreting Social Media
Slides
Lecture Video
25 Apr 25 Machine Translation
Slides
Lecture Video
Chap 25.0-1, 25.9 Final Project code due 11:59 PM
26 Apr 30 Deep Learning
Slides
Lecture Video
27 May 2 Conclusion
Slides
Lecture Video
Final Project report due 11:59pm
TBD Final exam

Competitive Project

A major component will be the project: build a program whose input is a web page P and whose output is a set of questions about the content in P (that a human could answer if she read P), and can also, if given a question Q about the content of P, answer the question intelligently. Projects will be pitted against each other in a competition at the end of the course.

Project Resources:

Grading

Students will be evaluated by exam (midterm and final, totaling 40%), regular short quizzes and weekly pencil-and-paper or small programming homework problems (30% together), and the group project (30%).

FAQ

Should I take this course?

Yes, if:

Related courses elsewhere (not exhaustive!)

University of California, Berkeley, Brown University, University of Colorado, Columbia University, Cornell University, University of Illinois at Urbana-Champaign, Johns Hopkins University, University of Maryland, New York University, University of Pennsylvania, Stanford University, University of Utah, University of Wisconsin-Madison