CSE 517 - Natural Language Processing (original) (raw)

Instructor: Yejin Choi (yejin at cs dot washington dot edu) Office hours: Fri 3:00pm - 4:00pm at CSE 578 (and by appointment)	TA: Nicholas FitzGerald (nfitz at cs dot washington dot edu) Office hours: Thu 1pm - 2pm @ CSE 218 (and by appointment) TA: Minjoon Seo (minjoon at cs dot washington dot edu) Office hours: Mon 3pm - 4pm @ CSE 021 (and by appointment)

Approximate Schedule

Week	Dates	Topics & Lecture Slides	Notes (Required)	Textbook & Recommended Reading
1	Jan 4, 6	I. Introduction [slides] II. Words: Language Models (LMs) [slides]	LM	JM 4.1-4; MS 6
2	Jan 11, 13	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 18, 20	III. Sequences: Hidden Markov Models (HMMs) [slides] V. Trees: Probabilistic Context Free Grammars (PCFG) [slides]	Forward-backward, PCFG	JM 6.6-6.8; JM 13-14; MS 11-12
4	Jan 25, 27	V. Trees: Grammar Refinement[slides] V. Trees: Dependency Grammars & Mildly Context-Sensitive Grammars [slides]	Lexicalized PCFG, Inside-outside	Edmond-Chu-Liu
5	Feb 1, 3	III. Sequences: Sequence Tagging [slides] IV. Learning (Feature-Rich Models): Log-Linear Models [slides] IV. Learning (Structural Graphical Models): Conditional Random Fields (CRFs) [slides]	LogLinear, MEMMs, CRFs
6	Feb 8, 10	VI. Translation: Alignment Models & Phrase-based MT [slides]	IBM Models 1 and 2, Phrase MT, EM	JM 25; MS 13
7	Feb 15, 17	VII. Semantics: Frame Semantics [slides] VII. Semantics: Distributed Semantics, Embeddings [slides]	JMv3 Vector Semantics, Dense Vectors, Frame Semantics	JM 19.4; JM 20.7
8	Feb 22, 24	VIII. Deep Learning: Neural Networks[slides]
9	Mar 1, 3	VIII. Deep Learning: More NNs
10	Mar 8, 10	VIII. 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 (1 written & 4 programming) (50%), in-class workbook (15%), final project (30%), and course/discussion board participation (5%).

Policies

Homework 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, written in your own words. You are expected to maintain the utmost level of academic integrity in the course.
Final projects can be pursued in groups.
You have 7 penalty-free late day credits that you can use at any time during the quarter. After you have used up all the penalty-free credits, we will apply a penalty of 20% of the maximum grade per additional late day. Being late by a partial day (e.g., 0.5 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