LING 572 - Advanced Statistical Methods in Natural Language Processing
Winter 2012
Syllabus


Days Time (P.M.) Classroom
Tuesdays and Thursdays 1:30-2:50 JHN 022

Instructor Teaching Assistant
Name: Gina-Anne Levow Michael Goodman
Email: levow@uw.edu goodmami@uw.edu
Office: Padelford B-201 Treehouse
Office Hours: Friday: 10:30-11:30 (before PhonLab)
or by appointment
Skype or Adobe, too
Tentatively Tuesday: 3-4pm

Course Evaluation

Course description

This course covers several important machine learning algorithms for natural language processing including decision trees, k-Nearest Neighbors, Naive Bayes, transformation-based learning, Support Vector Machines, Maximum Entropy and Conditional Random Fields. Students implement many of the algorithms and apply these algorithms to NLP tasks.

Textbook

There is no required textbook. Instead, the course readings will be drawn from contemporary articles and tutorials available online. Helpful background material can also be found in:

Prerequisites:

Course Resources

Grading

Course Mechanics

Additional detailed information on grading, collaboration, incompletes, etc.


Tentative schedule, subject to change without notice.

Date Topics Readings Assignment
out
Slides Adobe Connect
Recording
January 3 Intro to Stat. Methods;
Information Theory
M&S 2.2   pdf pptx Online Offline
January 5 Decision Trees
Environment
Decision Tree Tutorial HW1: Due 1/12 pptx pdf Online Offline
January 10 Decision Trees     pptx pdf Online Offline
January 12 K-Nearest Neighbors   HW2: Due 1/19 pptx pdf Online Offline
January 17 Naive Bayes McCallum and Nigam (1998)
Joachims (1997)
  pptx pdf OnlineOffline
January 19 Naive Bayes Wrap-up   HW3: Due 1/26 pptx pdf Online Offline
January 24 Feature Selection Chi square test tutorial   pptx pdf Online Offline
January 26 Chi-square & Maximum Entropy Ratnaparkhi (1997)
Berger et al. (1998)
HW4: Due 2/2
Reading Assignment: Due 2/2 (in class)
pdf pptx Online
Offline recordings in ShareSpace
January 31 MaxEnt: Modeling Chen and Rosenfeld (1999)   pptxpdf Online Offline
February 2 MaxEnt: Modeling: Decoding
Training; Smoothing
Ratnaparkhi (1996) HW #5: Due 2/9 pptx pdf Online Offline
February 7 MaxEnt: Case Study     pptx pdf Online Offline
February 9 Conditional Random Fields Sutton and McCallum (2006) HW6: Due 2/16
Reading #2: Due 2/16,1:30pm
pptx pdf Online Offline
February 14 Multi-class Classification     pdf Online Offline
February 16 Support Vector Machines Manning et al. (2008), Ch. 15 HW #7: Due 2/23 pptx pdf Online Offline
February 21 SVM   Reading #3: Due 2/28 pptx pdf Online Offline
February 23 libSVM   HW #8: Due 3/1
Reading #4: Due 3/1
pptx pdf Online Offline
February 28 Tree Kernel Collins and Duffy 2001   pptx pdf Online Offline
March 1 Transformation-based Learning Brill (1995) HW #9: 3/8 pptx pdf Online Offline
March 6 EM Collins (1997)   pptx pdf Online Offline
March 8 Semi-supervised Learning Yarowsky (1995)
McClosky et al. (2006)
  pptx pdf Online Offline