CSE 517 - Natural Language Processing

University of Washington Department of Computer Science & Engineering

CSE 517 -- Natural Language Processing [Winter 2019]
Lecture: WF 11:30 - 12:50PM ECE 045

CSE Home

About Us

Contact Info

Teaching Crew

Personnel	Contact	Office Hours
Instructor: Yejin Choi	yejin at cs dot washington dot edu	Thu 4:45pm - 5:45pm @ Allen 578 (and by appointment) Thu 5:15pm - 6:15pm on Jan 10
TA: Hannah Rashkin	(hrashkin at cs dot washington dot edu)	Fri 2:30 - 3:30 @ Gates 152 (and by appointment)
TA: Max Forbes	(mbforbes at cs dot washington dot edu)	Wed 2pm - 3pm @ Gates 151 (and by appointment)
TA: Rowan Zellers	(rowanz at cs dot washington dot edu)	Tue 4pm - 5pm @ Gates 153 (and by appointment)

Approximate Schedule

Week	Dates	Topics & Lecture Slides	Notes (Required)	Textbook & Recommended Reading
1	Jan 9, 11	I. Introduction [slides] II. Words: Language Models (LMs) [slides]	LM	JM 4.1-4; MS 6
2	Jan 16, 18	II. Words: Unknown Words (Smoothing) [slides] III. Sequences: Hidden Markov Models (HMMs) [slides]	HMM	JM 4.5-7; MS 6; JM 5.1-5.3; 6.1-6.5; MS 9, 10.1-10.3
3	Jan 23, 25	III. Sequences: Hidden Markov Models (HMMs) & EM [slides]	Forward-backward, EM	JM 5.1-5.3; 6.1-6.5; MS 9, 10.1-10.3
4	Jan 30, Feb 1	IV. Trees: Probabilistic Context Free Grammars (PCFG) [slides]	PCFG	JM 13-14; MS 11-12
5	Feb 6, 8	IV. Trees: PCFG Grammar Refinement [slides] IV. Trees: Dependency Grammars [slides] V. Learning - Feature-Rich Models: Log-Linear Models [slides]	Lexicalized PCFG, LogLinear	Inside-outside, Edmond-Chu-Liu JM 6.6-6.8;
6	Feb 13, 15	V. Learning - Graphical Models: Conditional Random Fields (CRFs) [slides]	MEMMs, CRFs
7	Feb 20, 22	VI. Semantics: Frame Semantics [slides] VI. Semantics: Distributed Semantics, Embeddings [slides]	Frame Semantics, JMv3 Vector Semantics, Dense Vectors	JM 19.4; JM 20.7
8	Feb 27, Mar 1	VII. Deep Learning: Neural Networks [slides]
9	Mar 6, 8	VII. Deep Learning: More NNs
10	Mar 13, 15	VII. Deep Learning: Yet More NNs

Textbooks

Recommended: [JM] Dan Jurafsky and James H. Martin, Speech and Language Processing: "An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition", Prentice Hall, Second Edition, 2009. (draft chapters of the third edition available online)
Optional: [MS] Chris Manning and Hinrich Schuetze, "Foundations of Statistical Natural Language Processing", Cambridge: MIT Press, 1999 (available online, free if accessed from UW network)
Optional: [GBC] Ian GoodFellow, Yoshua Bengio, and Aaron Courville, "Deep Learning" (free online book available at deeplearningbook.org )

Assignments, Discussion Board

Available at Canvas

Grading

The grade will consist of homeworks (written & programming) (55%), in-class workbooks (10%), final projects (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 7 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. You do NOT need to ask for our approval to use your unused late credits; Your late credits will be automatically deducted based on the timestamp of your submission.