Natural Language Processing Prof. Jason Eisner Course # 600.465 - Fall 2008 Announcements | Course Information | Schedule

Announcements

• 11/20/08 HW6 is available at 18 pages. It is due on December 8 at 2pm. (Remember that there is a hard deadline of December 14 even if you have > 6 late days left.) This is a programming assignment with a long handout, so start now!
• 11/11/08 HW5 is available at 10 pages. This is a relatively short assignment but involves some reading. It is due due in a week -- on Wednesday, 11/19 Monday, 11/24, at 2pm.
• 10/23/08 HW4 is available at 8 pages. It deals with attaching semantic λ-expressions to grammar rules. It is due on Monday, 11/10, at 2pm.
• 10/11/08 HW3 is available at 13 pages. This is the hardest assignment in the course, with two major challenges: probabilistic Earley parsing, and making parsing efficient. Get started now! It is due on Halloween at 2pm. You may work with a partner on this one.
• 9/19/08 HW2 is available and weighs in at 21 pages. It is due on Friday, 10/10, at 2pm. I suggest you start right away with the written exercises (questions 1-5), while the probability lectures are still fresh in your head. The remainder of the assignment (questions 6-14, plus extra credit opportuities) requires a computer and will take some time.
• 9/11/08 HW1 (10 pages) is available. Usually you should download homework assignments yourself from this webpage, but I handed this first one out in class today. It is due on Friday, 9/19, at 2pm: please get this one in on time so we can discuss it in class an hour later.
• 9/5/08 Today, Friday, is the first day of class (3pm MWF). The room is currently listed as CSEB B17 (basement auditorium) but may change.
• 9/5/08 Please bookmark this page (http://cs.jhu.edu/~jason/465).

Vital Statistics [1]

Welcome! This course is designed to introduce you to some of the problems and solutions of NLP, and their relation to linguistics and statistics. You need to know how to program (e.g., 600.120) and use common data structures (600.226). It might also be nice to have some previous familiarity with automata (600.271) and probabilities (550.310). At the end you should agree (I hope!) that language is subtle and interesting, feel some ownership over some of NLP's formal and statistical techniques, and be able to understand research papers in the field.

Course catalog entry: This course is an in-depth overview of techniques for processing human language. How should linguistic structure and meaning be represented? What algorithms can recover them from text? And crucially, how can we build statistical models to choose among the many legal answers? The course covers methods for trees (parsing and semantic interpretation), sequences (finite-state transduction such as morphology), and words (sense and phrase induction), with applications to practical engineering tasks such as information retrieval and extraction, text classification, part-of-speech tagging, speech recognition and machine translation. There are a number of structured but challenging programming assignments. Prerequisite: 600.226. [Eisner, Applications, Fall] 3 credits

Lectures:	MWF 3-4 pm (sometimes 3-4:30), CSEB B17
Prof:	Jason Eisner - ()
TA:	Jason Smith - ()
CA:	Eric Kim -
Office hrs:	For Prof: MW 4pm after class, or by appt in CSEB 324C For TA: M 11-12:30 in CSEB 323, or by appt
Mailing list:	probably ... public questions, discussion, announcements
Web page:	http://cs.jhu.edu/~jason/465
Textbook:	Jurafsky & Martin, 2nd ed. (semi-required - P98.J87 2009 in Science Ref section on C-Level) Manning & Schütze (recommended - online PDF version is accessible for free from within JHU)
Policies:	Grading: homework 45%, participation 10%, midterm 15%, final 30% Submission: via this web form Lateness: floating late days policy Honesty: here's what it means Intellectual engagement: much encouraged Announcements: Read mailing list and this page!
Related course sites:	List of many courses - some may have useful material!

[1] Or are these statistics? What is the scope of "statistics" anyway? Does it just mean "information"?

Schedule

This class is in the 3-4:30 time slot, a "flex slot" that is intended to permit either three 50-minute lectures or two 75-minute lectures per week. Usually, we have three 50-minute lectures per week (MWF). However, you will see on the schedule below that I am fairly likely to cancel class on M 9/29, M 10/27, W 11/19, and M 12/8. I may therefore ask you to let me make up the time with a few 75-minute lectures, for example, on M and W in the week before a canceled class.

Warning: For future lectures and assignments, the links below take you to last year's versions, which are subject to change.

Warning: The Jurafsky & Martin chapter numbers refer to the 1st edition, not the 2nd. We will update them shortly.

Department of Computer Science
The Johns Hopkins University
New Engineering Building Room 224
3400 North Charles Street
Baltimore, MD 21218
(410) 516-8775 (phone)
(410) 516-6134 (fax)

Last Modification $Date: 2008/11/17 18:55:56 $ (GMT)