CSE 447 - Natural Language Processing

University of Washington Department of Computer Science & Engineering

CSE 447 -- Natural Language Processing [Winter 2018]
Lecture: MWF 12:30pm-1:20pm in MOR 220
Section: [AA] Thu 12:30pm-1:20pm in MEB 103
Section: [AB] Thu 1:30pm-2:20pm in EE1 45

CSE Home

About Us

Contact Info

Teaching Crew

Personnel	Contact	Office Hours
Instructor: Yejin Choi	yejin at cs dot washington dot edu	Wed 4:30pm - 5:30pm @ CSE 578 (and by appointment)
TA: Luheng He	(luheng at cs dot washington dot edu)	Mon 3:30pm - 4:30pm @ CSE 021 (and by appointment)
TA: Phoebe Mulcaire	(pmulc at cs dot washington dot edu)	Wed 3:30pm - 4:30pm @ CSE 021 (and by appointment)
TA: Ari Holtzman	(ahai at cs dot washington dot edu)	Thu 4pm - 5pm @ CSE203 (and by appointment)
TA: Nelson Liu	(nfliu at cs dot washington dot edu)	Fri 3:30pm - 4:30pm @ CSE 220 (and by appointment)

Approximate Schedule

Week	Dates	Topics & Lecture Slides	Notes (Required)	Textbook & Recommended Reading
1	Jan 3, 5	I. Introduction [slides] II. Words: Language Models (LMs) [slides]	LM	JM 4.1-4; MS 6
2	Jan 8, 10, 12	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 17, 19 (Jan 15: MLK day)	III. Sequences: Hidden Markov Models (HMMs) & EM [slides]	Forward-backward, EM	JM 6.6-6.8; JM 13-14; MS 11-12
4	Jan 22, 24, 26	IV. Trees: Probabilistic Context Free Grammars (PCFG) [slides]	PCFG
5	Jan 29, 31, Feb 2	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
6	Feb 5, 7, 9	Guest Lecture: ``Verb Physics & Factor Graphs'' by Max Forbes on Feb 5 V. Learning (Structural Graphical Models):* Conditional Random Fields (CRFs) [slides]	MEMMs, CRFs
7	Feb 12, 14, 16	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 21, 23 (Feb 19: Presidents Day)	Guest Lecture: ``QA/Reading Comprehension'' by Eunsol Choi on Feb 21 VII. Deep Learning:* Neural Networks [slides]
9	Feb 26, 28, Mar 2	VII. Deep Learning: More NNs
10	Mar 5, 7, 9	VIII. Translation: Alignment Models & Phrase-based MT [slides]	IBM Models 1 and 2, Phrase MT, EM	JM 25; MS 13

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) (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.