CSE 517 - Natural Language Processing

University of Washington Department of Computer Science & Engineering

CSE 517 - Natural Language Processing - Winter 2013
Mon, Wed 1:30-2:50 in JHN 175

CSE Home

About Us

Contact Info

Instructor: Luke Zettlemoyer (lsz at cs dot washington dot edu)
Office hours: Tuesdays at 11 in CSE 658 (and by appointment) TA: Yoav Artzi (yoav at cs dot washington dot edu)
Office hours: Thursdays at 2:30 in CSE 390 (and by appointment)
(Plus: 2/20, 3-4pm, CSE 390. No office hours on 2/21, 2/28 and 3/7)

Schedule [WARNING: topics subject to change!]

Week	Dates	Topics & Lecture Slides	Notes	Textbook	Links
1	Jan 7, 9	Introduction; Language Modeling (LM)	LM Notes	J&M 4; M&S 6	[Smoothing] [Pitman-Yor] [Large LMs]
2	Jan 14, 16	Text Classification: Naive Bayes, Linear Models, EM	Naive Bayes, Log-linear models (Sec 2)	J&M 20-20.4; M&S 16.2-16.3	[Semi-supervised Naive Bayes] [MaxExt]
3	Jan 23	Hidden Markov Models (HMMs) and Tagging	HMM Notes, CRF Notes	J&M 5.1-5.3, 6.1-6.4; M&S 9, 10.1-10.3	[TnT Tagger] [Stanford Tagger] [SOTA POS]
4	Jan 28, 30	POS PCFGs and Parsing	PCFG Notes	J&M 14	[Best First] [A* Parsing]
5	Feb 4, 6	Parsing (cont.)	Lexicalized PCFGs	M&S 11-12	[Lexicalized] [Unlexicalized] [Split Merge]
6	Feb 11, 13	Intro to MT & Word Alignment	IBM Models 1 and 2	M&S 13; J&M 25.1-6	[IBM Models] [HMM Model]
7	Feb 20	Phrase-based MT	Phrase-based Notes	J&M 25.7-9	[Model] [Decoding] [Tuning]
8	Feb 25, 27	Syntax-based MT; Information Extraction (IE)		J&M 22.1-2	[Tree-to-String] [Hiero] [Tree-to-Tree] [Reordering]
9	Mar 4, 6	IE cont.; Co-reference		J&M 21.2-8
10	Mar 11, 13	Compositional Semantics		J&M 17.1-4

Textbooks

Recommended: D. Jurafsky & James H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition, Prentice Hall, Second Edition, 2009. (J&M)
Optional: C.D. Manning & H. Schuetze, Foundations of Statistical Natural Language Processing, Cambridge: MIT Press, 1999 (available online, free if accessed from UW computers) (M&S)

Contact

Please feel free to email the course staff, addresses above, and come to office hours. Let us know if you need to meet outside of the scheduled hours, we will do our best to accomodate.
We also have a GoPost discussion board. Please consider posting your questions there; everyone will benefit. We also encourage you to try to answer questions, which will count as class participation. We will monitor daily and contribute as long as the boards are being used.
Grades: Assignment grades are posted in the online CSE 517 Gradebook. Please let us know if you see any errors.

Homeworks

We will have 4-5 homework assignments, which will be listed below as they are assigned.

Assignment 1: Language Models [pdf] [data] (Due Fri Jan 18, 5pm)
Assignment 2: POS Tagging [pdf] (Due Wed Feb 6 ~~Tue Feb 5~~, 5pm)
Assignment 3: Parsing [pdf] (Due Sat Feb 23 ~~Wed Feb 20~~, 5pm)
Assignment 4: MT [pdf] (Due Fri Mar 8, 5pm ~~Tue Mar 5, 5pm~~)

Please submit your assignments to the online DropBox.

Final Mini-project

A final mini-project will completed during the last weeks of the term. Students are encouraged to design projects that overlap with their research interests. See the full description. Please email your project proposal to Luke by the proposal deadline (2/22, 5pm).

Grading

The final grade will consist of homeworks (60%), a final mini-project (30%), and course participation (10%). No midterm or final exam.

Course Administration and Policies

Assignments must be done individually unless otherwise specified. You may discuss the subject matter with other students in the class, but all final answers must be your own work. You are expected to maintain the utmost level of academic integrity in the course.
Assignments may be handed in up to a week late, at a penalty of 10% of the maximum grade per day.
Comments can be sent to the instructor or TA using this anonymous feedback form.

Department of Computer Science & Engineering
University of Washington
Box 352350
Seattle, WA 98195-2350
(206) 543-1695 voice, (206) 543-2969 FAX