Deep Processing Techniques for NLP
N.B.: If you are a student, please refer to the course page on Canvas. This page is purely for public-facing informational purposes and is not guaranteed to be up-to-date.
Basic Info
| Days | Time | Classroom |
| Mondays and Wednesdays | 3:30—4:50PM | DEN 212 |
| Instructor | Teaching Assistant | |
| Name | Ryan Georgi | Ajda Gokcen |
| Office | GUG 418-D | GUG 416-A (Treehouse Lab) |
| Contact | Use Canvas Inbox | |
| Office Hours | Wed 12:30-2:30 | M/W 2:00–3:00 or by Appt. |
Course Description
This course covers algorithms for associating deep or elaborated linguistic structures with naturally occurring data, covering parsing, semantics, and discourse.
Textbook
The course textbook is Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, 2nd edition, by Daniel Jurafsky and James Martin.
Prerequisites:
- CSE 373 (Data Structures) or Equivalent
- MATH/STAT 394 (Intro to Probability) or Equivalent
- Formal grammars, languages, and automata
- Programming in one or more of Java, Python, C/C++, or Perl
- Linux/Unix Commands
Course Resources:
- Zoom Meeting Room: https://washington.zoom.us/my/lingzoom
- Patas Account Request
- Computing Resources Orientation
- Condor Wiki Pages
Grading:
- 100%: Homework Assignments
- Up to 2% Adjustment for significant in-class or discussion participation
Course Policies
Course Schedule
| Date | Topics | Jurafsky & Martin | Addt’l Reading | Assignment | Slides |
| Sep 26 | Intro to Deep Processing for NLP; Syntax | Chapter 1, 12 | Patas and Condor | HW #1 – 9/28 | 1 – Intro |
| Oct 1 | CFGs and Parsing | Chapter 12, 13.1—13.3 | 2 – Grammars | ||
| Oct 3 | CKY; CNF | Chapter 13.4.1 | HW #2 – 10/5 | 3 – CKY | |
| Oct 8 | Parsing: CKY, Probablistic CKY | Chapter 14–14.2 | 4 – PCKY & PCFG | ||
| Oct 10 | PCFGs: Algorithms and Evaluation | Chapter 14.2–14.6 | HW #3 – 10/12 | 5 – PCKY & Eval | |
| Oct 15 | PCFGs: evaluation; improvement | Chapter 14.7–14.11 | 6 – PCFG & Improvements | ||
| Oct 17 | Dependency Parsing | Chapter 12.7 | De Marneffe et al, 2006 McDonald et al, 2005 |
HW #4 – 10/19 | 7 – Dependency Grammars |
| Oct 22 | Dependency Parsing (cont’d) + Features | Chapter 15–15.4 | 8 – OOV, Dep Parsing | ||
| Oct 24 | Semantics Intro | Chapter 17 | HW #5 – 10/26 | 9 – Computational Semantics | |
| Oct 29 | Semantics (cont’d) | Chapter 15.5–15.7; 17, 18 | 10 – More Computational Semantics | ||
| Oct 31 | Lambda Calculus Cont’d | Chapter 18.2 | Blackburn & Bos, 1999, 2.3–2.4 | HW #6 – 11/2 | 11 – Lexical Semantics |
| Nov 5 | Lexical, Distributional Semantics | Chapter 19.1–19.3, 20.1–20.4, 20.7, 20.10 | 12 – Distributional Semantics | ||
| Nov 7 | Distributional, Dictionary-based Models | Chapter 20 | HW #7 – 11/9 | 13 – Distributional Semantics 2 | |
| Nov 12 | Veterans’ Day; No Class | ||||
| Nov 14 | Thesaurus similarity | Chapter 19.4, 20.9 | Resnik WSD, esp. Sec 5.1 Jurafsky&Gildea, 2002, p. 1-19. |
HW #8 – 11/16 | 14 – Word Sense Disambiguation |
| Nov 19 | Semantic Role Labeling | Chapter 20, 21.0 | 15 – SRL | ||
| Nov 21 | Computational Discourse, Reference | Chapter 21.4–21.8 | Ragunathan et al, 2010 | 16 – Discourse & Coref | |
| Nov 26 | Computational Discourse Structure | Ch. 21.1–21.3 | Hobbs (1978) | HW #9 – 11/30 | 17 – Discourse & Coref Continued |
| Nov 28 | Discourse Structure & Case Study | 18 – Other Approaches to Discourse | |||
| Dec 3 | Wrap-Up: Current Advances | 19 – Wrap-Up: Current Advances | |||
| Dec 5 | Wrap-up: Unsupervised Methods | 20 – Unsupervised Methods | |||