Natural Language Processing Prof. Jason Eisner Course # 600.465 — Fall 2012 Announcements | Course Information | Schedule

Announcements

• 11/28/12 The first half of HW7 is available. An updated version with the complete assignment will be posted as soon as we're done testing. It is due on Friday, December 7, at 11:59pm (as late as we could make it without cutting into reading period). Remember that there is a hard deadline of December 16 even if you have lots of late days left. [See Piazza for further updates on HW7.]
• 11/5/12 HW6 is available at 16 pages. It is due on Monday, November 19 at 2pm. This is a programming assignment with a long handout, so start as soon as possible!
• 10/27/12 HW5 is available at 8 pages. It deals with attaching semantic λ-expressions to grammar rules. It is due on Friday, 11/9, at 2pm.
• 10/10/12 HW4 is available at 12 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. 29 at 2pm. You may work with a partner on this one.
• 9/28/12 HW3 (23 pages plus extra credit problems!) is available. The due date is extended to Wednesday, 10/10, 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 of it this week, and half next week.
• 9/19/12 HW2 (15 pages) is available. This assignment requires no programming; it's just about manipulating probabilities. However, it involves some reading, experimenting with an applet, and answering various short questions. It is due in a week (Wednesday 9/26 at 2pm).
• 9/7/12 HW1 (10 pages) is available. It is due on Wednesday, 9/19, at 2pm: please get this one in on time so we can discuss it in class an hour later.
• 9/5/12 Monday is the first day of class (3pm MWF). The room is Hodson 313.
• 9/5/12 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 or 3-4:15, Hodson 313
Prof:	Jason Eisner - ()
TA:	Frank Ferraro - (ferraro at cs dot jhu dot edu)
CA:	Katherine Wu -
Office hrs:	For Prof: After class until 4:30, or by appt, in Hackerman 324C For TA/CA: TBA
Discussion session:	TA-led session (optional) for activities/discussion/questions/review: TBA
Discussion site:	http://piazza.com/class#fall2012/600465 ... 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

Note: This class is in the "flex time slot" from 3-4:30. We will use the time for a combination of lecture and discussion. Class will often run 3-4, followed by office hours from 4-4:30. However, class will sometimes run till 4:15 in order to keep up with the syllabus. I'll try to give advance notice of these "long classes," which among other things make up for days when the professor will be out of town.

Warning: The schedule may change. Links to future lectures and assignments may also change (they currently point to last year's versions).

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

• The XFST finite-state toolkit; Porter stemming

• 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: 2013/01/09 21:48:58 $ (GMT)