CSE 447/547 - Natural Language Processing

University of Washington Department of Computer Science & Engineering

CSE 447/547 -- Natural Language Processing [Winter 2020]
Lecture: MWF 10:30pm-11:20am in CSE2 G01
Section: [AA] Thu 12:30pm-1:20pm in MOR220
Section: [AB] Thu 1:30pm-2:20pm in ARCG070
Section: [AC] Thu 2:30pm-3:20pm in MEB242

CSE Home

About Us

Contact Info

Teaching Crew

Personnel	Contact	Office Hours
Instructor: Yejin Choi	yejin at cs dot washington dot edu	Tue 4:30pm - 5:30pm @ CSE 578 (and by appointment)
TA: Maxwell Forbes	mbforbes at cs dot washington dot edu	Tue 2:30pm - 3:30pm @ CSE2 151 (and by appointment)
TA: Saadia Gabriel	skgabrie at cs dot washington dot edu	Thu 10:30am - 11:20am @ CSE2 121 (and by appointment)
TA: Peter West	pawest at cs dot washington dot edu	Wed 3:30pm - 4:20pm @ CSE2 153 (and by appointment)
TA: Dianqi Li	dianqili at uw dot edu	Tue 10:30 - 11:20am @ CSE2 153 (and by appointment)
TA: Jeff Da	jzda at cs dot washington dot edu	Mon 3:30pm - 4:20pm @ CSE2 131 (and by appointment)
TA: Michael Zhang	mjqzhang at cs dot washington dot edu	Wed 1:00pm - 2:00pm @ CSE2 121 (and by appointment)

Approximate Schedule

Week	Dates	Topics & Lecture Slides	Notes (Required)	Textbook & Recommended Reading
1	Jan 6, 8, 10	I. Introduction [slides] II. Words: Language Models (LMs) [slides]	LM	JM 4.1-4; MS 6
2	Jan 13, 15, 17	II. Words: Unknown Words (Smoothing) [slides]		JM 4.5-7; MS 6; JM 5.1-5.3; 6.1-6.5; MS 9, 10.1-10.3
3	Jan 22, 24 (Jan 20: MLK day)	III. Sequences: Hidden Markov Models (HMMs) [slides]	HMM	JM 6.6-6.8; JM 13-14; MS 11-12
4	Jan 27, 29, 31	III. Sequences: Hidden Markov Models (HMMs) & EM [slides]	Forward-backward, EM
5	Feb 3, 5, 7	V. Learning (Feature-Rich Models): Log-Linear Models [slides] *Guest Lecture on Feb 7	LogLinear MEMMs, CRFs
6	Feb 10, 12, 14	Guest Lecture on Feb 10 V. Learning (Structural Graphical Models):* Conditional Random Fields (CRFs) [slides]	LogLinear MEMMs, CRFs
7	Feb 19, 21 (Feb 17: Presidents Day)	VII. Deep Learning for NLP [slides]
8	Feb 24, 26, 28	VII. Deep Learning for NLP [slides]
9	Mar 2, 4, 6	VII. Deep Learning for NLP VI. Semantics: From Distributed Semantics to Neural Embeddings [slides]	JMv3 Vector Semantics, Dense Vectors	JM 19.4; JM 20.7
10	Mar 9, 11, 13	IV. Trees: PCFG[slides] IV. Trees: Dependency Grammars [slides]	PCFG, Lexicalized PCFG, Inside-outside Edmond-Chu-Liu

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) (60%), in-class quizzes (10%), final exam (25%), 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.