Natural Language Processing

11-411 for undergrads | 11-611 for grads

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
  • translation,
  • summarization,
  • extracting information,
  • question answering,
  • natural interfaces to databases, and
  • conversational agents.

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.

Lectures

Date Topic Readings Assignments and
Project milestones
1 Aug 28 Course overview; What does it mean to know language?
Slides
Lecture Video
Chap 1
2 Aug 30 Information extraction, question answering, and NLP
in IR
Slides
Lecture Video
Chap 22.0-2, 23.0-2
- Aug 31 Assignment 00
AutoLab(Assignment 00)
Due on 5th Sep 2019, 11:59 PM EST
- Sep 1 Assignment 01
AutoLab(Assignment 01)
Due on 17th Sep 2019, 11:59 PM EST
3 Sep 4 Project
Slides -- Example video
4 Sep 6 Words, morphology, and lexicons
Slides
Lecture Video
Chap 3.1-3.9
5 Sep 11 Language models and smoothing
Slides
Lecture Video
Chap 4.3-8
6 Sep 13 Noisy channel models and edit distance
Slides
Slides (Distance Metrics)
Chap 3.10, 3.11, 5.9
7 Sep 18 Classification
Slides
Lecture Video
Assignment 1 due (Sep 17th 11:59 PM)
8 Sep 20 Part of speech tags
Slides
Lecture Video
Chap 5.0-3
9 Sep 25 Hidden Markov models
Slides
Lecture Video
Chap 6.0-4
10 Sep 27 Syntactic representations of natural language
Slides
Lecture Video
Chap 12.0-3 Assignment 2 due (Sep 26th 11:59 PM)
11 Oct 2 Chomsky hierarchy and natural language
Slides
Lecture Video
Chap 15 Preliminary Project Report due
12 Oct 4 Context-free recognition, CKY
Slides
Lecture Video
Assignment 3 due (Oct 6 11:59 PM)
13 Oct 9 Parsing algorithms
Slides
Lecture Video
Chap 13
14 Oct 11 Parsing algorithms contd.
Slides
Lecture Video
Chap 12.7, Chap 14-14.2
15 Oct 16 Treebanks and PCFGs
Slides
Lecture Video
Chap 12.4, 14.7 Assignment 4 due (Oct 15 11:59 PM)
Oct 18 Midterm exam
Practice Problems
Practice Solutions
16 Oct 23 Lexical semantics
Slides
Lecture Video
Chap 17.0-2, 19.0-3 Project Progress Report due
17 Oct 25 Word embeddings/vector semantics
Slides
Lecture Video
SLP3 Chap 6
18 Oct 30 Verb/sentence semantics
Slides A
Slides B
Chap 17.2-4, Chap 19.4-6 Assignment 5 due (Oct 29 11:59 PM)
19 Nov 1 Compositional semantics, semantic parsing
Slides
Chap 18.1-3
20 Nov 6 Discourse, entity linking, pragmatics
Slides
Lecture Video
Chap 21
21 Nov 8 Word Sense Disambiguation and Semantic Role Labelling
Slides
Lecture Video
Chap 20.0-6, 20.8-11 Assignment 6 due (Nov 7 11:59 PM)
22 Nov 13 Speech 1
Slides
23 Nov 15 Speech 2
Project dry run code due
Nov 20 Thanksgiving Assignment 7 due (Nov 19 11:59 PM)
24 Nov 22 Interpreting Social Media
Slides A
Slides B
Slides C
Slides D
25 Nov 27 Deep Learning
Final Project code due
26 Nov 29 Machine Translation
Chap 25.0-1, 25.9
27 Dec 4 Non-English NLP
28 Dec 6 Conclusion

Final Project report due
TBA 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.

Evaluation

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:

  • you're a CS student interested in languages, language technology, or information processing
  • you're a CS student who needs an "applications" credit
  • you're a language technology minor (this course is an elective option)
  • you're a linguistics student who can write computer programs (this course is an elective option)
  • you always suspected natural language was kind of like Lisp (or Java or ...)
  • you want computers to take over the world
  • you don't want computers to take over the world, but if they do, you want to negotiate your release
  • you like AI, machine learning, and/or theoretical computer science, and want to apply them to a hard real-world problem

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