CSE 490 U - Natural Language Processing

University of Washington Department of Computer Science & Engineering

CSE 490 U - Natural Language Processing - Spring 2016
Lecture: MWF 10:30am-11:20am in MGH 287
Section: Thu 9:30am-10:20am in LOW 105

CSE Home

About Us

Contact Info

Instructor: Yejin Choi (yejin at cs dot washington dot edu)
Office hours: Wed 4:30pm - 5:30pm at CSE 578 (and by appointment) TA: Luheng He (luheng at cs dot washington dot edu)
Office hours: Tue 5pm - 5:45pm at CSE 218
TA: Maarten Sap (msap at cs dot washington dot edu)
Office hours: Thu 2pm - 2:45pm at CSE 218

Tentative Schedule

Week	Dates	Topics & Lecture Slides	Notes (Required)	Textbook & Recommended Reading
1	Mar 28, 30, Apr 1	I. Introduction [Slides] II. Words: Language Models (LMs) [Slides]	LM	J&M 4.1-4; M&S 6
2	Apr 4, 6, 8	II. Words: Language Models (LMs), Smoothing [Slides] III. Sequences: Hidden Markov Models (HMMs) [Slides]	HMM	J&M 4.5-7; M&S 6
3	Apr 11, 13, 15	III. Sequences: Hidden Markov Models (HMMs) [Slides] III. Sequences: Part-Of-Speech Tagging (skipped) [Slides]	Forward-backward	J&M 5.1-5.3; 6.1-6.5; M&S 9, 10.1-10.3
4	Apr 18, 20, 22	IV. Trees: Probabilistic Context Free Grammars (PCFG) [Slides]	PCFG	J&M 13-14; M&S 11-12
5	Apr 25, 27, 29	IV. Trees: PCFG Grammar Refinement [Slides]	Lexicalized PCFG, Inside-outside	J&M 13-14; M&S 11-12
6	May 2, 4, 6	IV. Trees: Dependency Grammars and Mildly Context-Sensitive Grammars [Slides]		Edmond-Chu-Liu;
7	May 9, 11, 13	V. Semantics: Frame Semantics [Slides]; V. Semantics: Distributed Semantics, Embeddings [Slides]	J&Mv3 Vector Semantics, Dense Vectors, Frame Semantics	J&M 19.4; J&M 20.7
8	May 16, 18, 20	VI. Learning: Log-Linear Models, Conditional Random Fields (CRFs) [Slides]	LogLinear, MEMMs, CRFs	J&M 6.6 - 6.8
9	May 23, 25, 27	VI. Learning: Deep Learning[Slides]		Russell & Norvig Ch 18.7 ANNs; Bishop Ch 5 ANNs;
10	(May 30), Jun 1, Jun 3	VII. Translation: Alignment Models & Phrase-based MT [Slides]	IBM Models 1 and 2, Phrase MT, EM	J&M 25; M&S 13

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)

The draft chapters of the third edition are available online!

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)

Grading

The grade will consist of homeworks (written & programming) (50%), in-class quizzes (15%), final exam (30%), and course/discussion board participation (5%).

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.
Each assignment may be handed in up to three days late, at a penalty of 20% of the maximum grade per day. You have 5 penelty-free late day credits that you can use at any time during the quarter. Above 20% substraction will apply only after you have used all your late day credits. Being late by a partial day (e.g., 1 hour) will be rounded up to 1 full day.

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