CS 4705: Introduction to Natural Language Processing, Fall 2004 |
|||
Time: |
MW 1:10-2:25 |
Place |
Mudd 545 |
Professor: |
Office Hours: |
M 2:30-3:30;Th 3:30-4:30,
CEPSR 705 |
|
Email: |
julia@cs.columbia.edu |
Phone: |
212-939-7114 |
Teaching
Assistant: |
Office Hours: |
MW 4-5 |
|
Email: |
smaskey@cs.columbia.edu |
Phone: |
212-939-7116 |
Announcements
|| News|| Academic
Integrity ||
Contributions
|| Description
Links
to Resources
|| Requirements
|| Syllabus ||
Text
This course provides an introduction to the field of computational linguistics, aka natural language processing (NLP) - the creation of computer programs that can understand, generate, and learn natural language. We will study the three major subfields of NLP: syntax (the structure of an utterance), semantics (the truth-functional meaning of an utterance), and pragmatics/discourse (the context-dependent meaning of an utterance). The course will introduce both linguistic (knowledge-based) and statistical approaches to language processing, and will illustate the use of such methods in a variety of text- and speech-based application areas, including spoken dialogue systems, speech recognition and synthesis, machine translation, and language summarization.
Speech and Language Processing by Jurafsky and Martin. It will be available from the Morningside Bookshop (was Papyrus Books), as well as from Amazon and other online providers. It should also be on reserve in the Engineering Library. Please check the online errata for the text for each chapter as you read it.
Three homework assignments, a midterm and a final exam. Graduate students will have one additional assignment. Each student in the course is allowed a total of 5 late days on homeworks with no questions asked; after that, points will be deducted for late submission, unless you have a note from your doctor. Do not use these up early! Save them for real emergencies. Homeworks are due by midnight on the due date.
All students are required to have a Computer Science Account for this class. To sign up for one, go to the CRF website and then click on "Apply for an Account".
Homework submission procedure.
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.
Each summary takes about 1 hour, depending on how many news articles are in the current set. Compensation depends on the number of news articles you summarize, but comes to about $10/hr.
Your participation will be greatly appreciated, but your course grade will not affected one way or the other.
You will be asked to write a 6 sentence summary of a cluster of news articles, with cross-references to the news sources. Instructions and links to the articles will be provided. Most of the work can be done by email, but you must show up in person to get paid. Please contact becky@cs.columbia.edu.
Qualifications: Good verbal skills, fluent reader/writer. Prefer demonstrated excellence in verbal skills, e.g., English Majors, Journalism Majors, high scores on verbal GRE/SAT.
Week |
Class |
Topic |
Reading |
Assignments |
1 |
Sep 8 |
|
|
|
|
Sep 13 |
Ch 1-2 |
|
|
2 |
Sep 15 |
Ch 3 |
Homework
1 Assigned (nb: Homework
submission procedure) |
|
|
Sep 20 |
Ch 4 |
|
|
3 |
Sep 22 |
Ch 6 |
Guest Speaker: Sameer Maskey |
|
|
Sep 27 |
Ch 5 |
|
|
4 |
Sep 29 |
Ch 7 |
|
|
|
Oct 4 |
Ch 8 |
Guest Speaker: Martin Jansche |
|
5 |
Oct 6 |
Ch 9 |
Guest Speaker: Owen Rambow |
|
|
Oct 11 |
Ch 10:1-3 |
Homework 1 due; Homework 2
assigned |
|
|
Oct 13 |
Ch 10:4-6; 11:0-3 |
|
|
7 |
Oct 18 |
Probabilistic and
Lexicalized Parsing |
Ch 12 |
|
|
Oct 20 |
|
|
Midterm Examination; Grad
assignment paper list due |
8 |
Oct 25 |
Ch 14-15 (15.1-3 opt) |
|
|
|
Oct 27 |
Ch 16 |
|
|
|
Nov 1 |
|
|
Holiday |
9 |
Nov 3 |
Ch 17.1-2, TBA |
|
|
|
Nov 8 |
Ch 17.3-5 |
Homework 2 due |
|
|
Nov 10 |
Homework 3 assigned |
||
11 |
Nov 15 |
Ch 18.2-3,5; Grosz&Sidner86 |
|
|
|
Nov 17 |
Ch 18.1,4 |
|
|
12 |
Nov 22 |
|
||
|
Nov 24 |
Ch 4.7 |
|
|
|
Nov 25 |
|
|
Thanksgiving Holiday |
13 |
Nov 29 |
Ch 19 |
|
|
14 |
Dec 1 |
Ch 20 |
Homework 3 due |
|
|
Dec 6 |
Ch 21 |
|
|
15 |
Dec 8 |
Speech and Text
Summarization |
|
|
|
Dec. 13 |
Summing Up: NLP Research
and Applications |
|
|
|
Dec. ? |
|
|
Final Examination |
Places to look up definitions and descriptions of terminology:
Try out one of the many versions of Eliza on the web.
AT&T Labs -
Announcements
|| Academic
Integrity ||
Contributions
|| Description
Links
to Resources
|| Requirements
|| Syllabus ||
Text