LING 570 - Shallow Processing Techniques for Natural Language Processing
Autumn 2011
Syllabus

Days Time (P.M.) Classroom
Mondays and Wednesdays 3:30-4:50 Savery 138

Instructor Teaching Assistant
Name: Gina-Anne Levow Sanghoun Song
Email: levow@uw.edu sanghoun@uw.edu
Office: Padelford B-201 Lewis Annex 110
Office Hours: Friday: 10-11 (before treehouse)
or by appointment
Skype or Adobe, too 		Mon: 12:13-1:30 (Tentative)

Course description

This course covers techniques and algorithms for associating relatively surface-level structures and information with natural language corpora, including POS tagging, morphological analysis, preprocessing/segmentation, named-entity recognition, chunk parsing, and word-sense disambiguation. Examines linguistic resources that can be leveraged for these tasks (e.g., WordNet).

Textbook

The course textbook is Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, 2nd edition, by Daniel Jurafsky and James Martin.

Prerequisites:

Course Resources

Grading

Course Mechanics

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

Tentative schedule, subject to change without notice.

Note about offline recordings: As of 10/19/11, Offline versions of lecture recordings will be stored on patas in ~/dropbox/11-12/570/recordings/ due to web site storage limitations.

Date Topics Jurafsky &
Martin 		Additional
Readings 		Assignment
out 		Slides Adobe Connect
Recording
September 28 Intro to Shallow Processing for NLP; Tokenization Chapter 1, 2   HW1: Due 10/5 pptx pdf Online
October 3 Formal languages, grammars; Regular expressions; Automata Chapter 2     pptx pdf Online
October 5 FSA; Carmel Chapter 2   HW2: FSA; Due 10/12 pptx pdf Online
October 10 FST Chapter 3.1-3.8     pdf pptx Online
October 12 Morphological Analysis Chapter 3.1-3.8   HW3: FST: Due 10/19 pptx pdf Online Offline
October 17 Morphology; Summary;
Language Modeling 		Chapter 3; Chapter 4.1-4.4     pptx pdf Online Offline
October 19 Language Modeling; Smoothing Chapter 4   HW4: Due 10/26 pptx pdf Online
October 24 Smoothing Chapter 4     pptx pdf Online
October 26 POS tagging Chapter 5   HW5: Due 11/2 pptx pdf Online offline
October 31 Hidden Markov Models: Def Chapter 6     pdf pptx Online Offline
November 2 POS tagging: Ngrams/HMMs Chapter 5   HW6: Due 11/9 pptx pdf Online -beginning Online Offline Offline -beginning
November 7 HMM (Cont'd) Chapter 6     pptx pdf Online Offline
November 9 Classification Chapter 6   HW#7: Due 11/16 pptx pdf Online
November 14 Mallet       pptx pdf Online
November 16 POS tagging: MaxEnt   Ratnaparkhi 1996 HW8: Due 11/23 pptx pdf Online
November 21 POS tagging: MaxEnt       pptx pdf Online Offline
November 23 Named Entity Recognition; Chunking J&M 22.1; J&M 13.5   HW9: Due 12/1
(a day later than usual) 		pptx pdf Online Offline
November 28 NER; Chunking J&M 22.1; J&M 13.5     pptx pdf Online
November 30 Clustering   Manning & Scheutze, Ch. 14 IR clustering HW #10: Due 12/8 pptx pdf Online Offline
December 5 Information Extraction Chapter 22     pptx pdf Online Offline
December 7 Review       pptx pdf Online