Steam-powered Turing Machine 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    Search    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
3Jan 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

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