Steam-powered Turing Machine University of Washington Department of Computer Science & Engineering
CSE 517 - Natural Language Processing - Winter 2015
Mon, Wed 1:30-2:50 in MGH 254
  CSE Home  About Us    Search    Contact Info 

Instructor: Yejin Choi (yejin at cs dot washington dot edu)
Office hours: Mondays at 3 - 4pm at CSE 578 (and by appointment)
TA: Eunsol Choi (eunsol at cs dot washington dot edu)
Office hours: Wednesdays 11am - noon at CSE 394 (and by appointment)
TA: Andrea M. Kahn (amkahn at uw dot edu)
Office hours: Thursdays 2 - 3pm at CSE 021 (and by appointment)

Schedule (subject to change)

Week Dates Topics & Lecture Slides Notes (Required) Textbook Supplementary Readings
1 Jan 5, 7 Introduction [Slides]; Language Models (LM) [Slides] LM Notes J&M 4.1-4; M&S 6 [Large LMs] [Berkeley LM]
2 Jan 12, 14 Sequences: Language Models and Smoothing; Hidden Markov Models (HMMs) [Slides] HMM Notes J&M 4.5-7; M&S 6 [Smoothing]
3Jan 21 Hidden Markov Models (HMMs) [Slides (Jan26)]& Part-Of-Speech Tagging [Slides (Jan26)] J&M 5.1-5.3; 6.1-6.4; M&S 9, 10.1-10.3 [TnT Tagger] [Stanford Tagger] [SOTA POS]
4 Jan 26, 28 Trees: Probabilistic Context Free Grammars (PCFG) and Parsing [Slides (Feb2)] PCFG Notes, Lexicalized PCFGs J&M 13-14; M&S 11-12 [Syntax Intro] [Incremental] [Best First] [A* Parsing] [Lexicalized] [Unlexicalized] [Split Merge]
5 Feb 2, 4 More Parsing [Slides (Feb2)]; Expectation Maximization (EM)[Slides] EM Notes, Forward-backward, Inside-outside J&M 6.5; M&S 9.3-4; 11.3-4 [Semi-supervised Naive Bayes] [EM Tutorial] [EM for Feature-Rich]
6 Feb 9, 11 Semantics: Frame Semantics [Slides (Feb2)]; Distributional Semantics J&M 19.4; 20.7; 20.9; M&S 8 [Fillmore-Tribute Workshop] [Frame-Semantic Parsing] [Composition in Distributional Models]
7 Feb 18 Machine Translation (MT): Word Alignment [Slides] IBM Models 1 and 2 J&M 25.1-6; M&S 13 [IBM Models] [HMM Model] [MERT Training]
8 Feb 23, 25 Phrase-based MT [Slides]; Syntax-based MT [Slides I] [II] Phrase-based Notes J&M 25.6-10; M&S 13 [SCFG Tutorial] [Hiero] [Tree-to-String] [Tree-to-Tree]
9 Mar 2, 4 Log-Linear / Feature-Rich Models: Conditional Random Fields (CRFs) [Slides] Log-linear models CRF Notes J&M 6.6-6.8; M&S 16.2-16.3 [MaxExt] [CRF Tutorial] [CRF LM] [CRF Parsing]
10 Mar 9, 11 Knowledge & Semantic Relations: Information Extraction; Entailment; [Slides] J&M 22 [Entailment Graphs] [Paraphrasing w/ MT] [Paraphrasing and Entailment]

Textbooks

Contact

Homeworks

We will have 4 programming-based homework assignments (60% of grade). Data/code/instruction are linked at Dropbox In addition, there will be lightweight 2 written homework assignments (15% of grade). Please submit all your assignments to the online DropBox.

Final Mini-project

A final mini-project (20% of grade) will be completed during the last weeks of the term. Students are encouraged to design projects that overlap with their research interests.

Grading

The final grade will consist of programming-based homeworks (60%), a final mini-project (20%), non-programming assignments (15%) and course/discussion board participation (5%). No midterm or final exam.

Course Administration and Policies


CSE logo Department of Computer Science & Engineering
University of Washington
Box 352350
Seattle, WA  98195-2350
(206) 543-1695 voice, (206) 543-2969 FAX