Natural Language Processing Prof. Jason Eisner Course # 600.465 - Fall 2011 Announcements | Course Information | Schedule

Announcements

• 11/26/11 HW7 is available at 10 pages. This is a relatively short assignment but involves some reading. It is due in about a week - on Sunday, 12/4, at 2pm. (Remember that there is a hard deadline of Sunday, December 11 even if you have > 5 late days left.)
• 10/29/11 HW6 is available at 16 pages. It is due on Friday, November 18 at 2pm. This is a programming assignment with a long handout, so start as soon as possible!
• 10/17/11 HW5 is available at 8 pages. It deals with attaching semantic λ-expressions to grammar rules. It is due on Friday, 11/4, at 2pm.
• Midterm was on Wednesday 10/19, in our usual classroom, from 3-4:30.
• 10/5/11 HW4 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 Oct. 24 at 2pm. You may work with a partner on this one.
• 9/23/11 HW3 (22 pages plus extra credit problems!) is available. Because we're getting it out late, the due date is extended to Wednesday, 10/5, at 2pm. Start early: This is a detailed assignment that requires you to write some annoying programs for smoothing and experiment with their parameters to see what happens. I strongly suggest you do half this week and half next week.
• 9/12/11 HW2 (8 pages) is available. This assignment requires no programming; it's just about manipulating probabilities. It is due in a week (Monday 9/19 at 2pm).
• 9/1/11 HW1 (10 pages) is available. It is due on Monday, 9/12, at 2pm: please get this one in on time so we can discuss it in class an hour later.
• 8/29/11 Monday is the first day of class (3pm MWF). The room is Hackerman B17.
• 8/29/11 Please bookmark this page (http://cs.jhu.edu/~jason/465).

Vital Statistics ^[1]

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 tagging and 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 or equivalent. [Eisner, Applications, Fall] 3 credits

More information: 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 (600.475, 550.420, or 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.

Lectures:	MWF 3-4 pm (sometimes 3-4:30), Hackerman B17
Prof:	Jason Eisner - ()
TA:	Xuchen Yao - (xuchen at cs dot jhu dot edu)
CA:	TBA
Office hrs:	For Prof: MW 4pm after class (or by appt) in Hackerman 324C For TA: M 12-1, Th 11-12, in Hackerman 226
Discussion session:	TA-led session (optional) for activities/discussion/questions/review: Th 3:30-4:30, in Hackerman 306
Discussion site:	http://piazza.com/class#fall2011/600465 ... 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) Roark & Sproat (recommended - P98.R63 2007 in same section) Manning & Schütze (recommended - free online PDF version here!)
Policies:	Grading: homework 50%, participation 5%, midterm 15%, final 30% Submission: TBA Lateness: floating late days policy Honesty: here's what it means Intellectual engagement: much encouraged Announcements: Read mailing list and this page!
Related sites:	List of many courses - some may have useful material!

[1] Or are these statistics? What are "statistics" anyway? How are they different from "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. Please try to keep the whole slot free, especially on MW:

• For office hours. Usually, we have three 50-minute lectures per week (MWF). On MW, I use the remainder of the slot (till 4:30) to hold office hours right after class.
• For emergencies. Occasionally, if I have to cancel a 50-minute class for some reason (e.g., on 9/28), I may ask you to let me make up the time by extending two lectures to 75 minutes, for example, on M and W of an adjacent week.
• For extra innings. Sometimes we're in the middle of something when the bell rings at 3:50. To me, at least, it sometimes seems wiser to finish it than to lose our place over some artificial deadline. (Hey, I give you late days and all I ask in return is some late minutes ...)

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

Warning: I sometimes turn off the PDF links when they are not up to date with the PPT links. If they don't work, just click on "ppt" instead.

Old Materials

• Grouping words (ppt): Semantic clustering
  • Clustering spreadsheet
• Splitting words (ppt): Word sense disambiguation and the Yarowsky algorithm
• Words vs. terms in IR (ppt): Collocation discovery and Latent Semantic Indexing
• Text categorization (ppt)
• Learning in the limit (ppt): Gold's theorem
• Knowledge extraction and dialogue systems (ppt)
• Machine translation:
  • Competitive linking (ppt): A simple bitext alignment algorithm
  • IBM Model 1 (guest lecture)
  • Phrase-based models and decoding (guest lecture)
• Applied NLP tasks:
  • named entity recognition (ppt) (guest lecture)
  • entity disambiguation and linking, question answering, sentiment analysis, dependency parsing, semantic role labeling (ppt) (guest lecture)

Last Modification $Date: 2012/01/21 07:21:39 $ (GMT)