Steam-powered Turing Machine 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    Search    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
3Jan 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 V. Trees: Probabilistic Context Free Grammars (PCFG) [slides]
V. Trees: Dependency Grammars [slides]
PCFG, Lexicalized PCFG, Inside-outside Edmond-Chu-Liu
5 Jan 29, 31, Feb 2 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 5, 7, 9 *Guest Lecture: ``Verb Physics & Factor Graphs'' by Max Forbes on Feb 5
VI. Semantics: Frame Semantics [slides]
VI. Semantics: Distributed Semantics, Embeddings [slides]
JMv3 Vector Semantics, Dense Vectors,
Frame Semantics
JM 19.4; JM 20.7
7 Feb 12, 14, 16 VI. Semantics: Distributed Semantics, Embeddings [slides]
VII. Deep Learning: Neural Networks [slides]
JMv3 Vector Semantics, Dense Vectors JM 19.4; JM 20.7
8 Feb 21, 23
(Feb 19: Presidents Day)
*Guest Lecture:
VII. Deep Learning: More NNs [slides]
9 Feb 26, 28, Mar 2 VII. Deep Learning: Even 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

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