This course covers algorithms for associating deep or elaborated linguistic structures with naturally occurring data, covering parsing, semantics, and discourse.
|Monday and Wednesday||1:00 - 2:20 PM||Loew 206|
Note: while lectures will be delivered live at the above time and location, they will also be recorded and posted to the course Canvas page.
|Instructor||Shane Steinert-Threlkeld||GUG 418D
|M 2:30-3:30PM Pacific
W 2:30-3:30PM Pacific
|Teaching Assistant||Haotian Zhu||T 12:00-1:00PM Pacific
F 3:00-4:00PM Pacific
|In person (location TBA)
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.
A draft copy of the book is available here.
N.B.: The authors have a nearly-complete draft of the 3rd edition available online. Essentially every chapter that we use in this course has a corresponding version in that edition. The chapters referenced below are from the 2nd edition, but you can find the corresponding chapter in the 3rd edition either by using the website for the 3rd or by looking at the detailed table of contents on the Amazon page for the 2nd edition or here.
N.B.: All homework grading will take place on the patas cluster using Condor, so your code must run there. I strongly encourage you to ensure you have an account set up by the time of the first course meeting.
Unless explicitly mentioned below, the shared policies of the LING 57x course series apply to this course. Please read those policies for more information.
This quarter is unprecedented, as we navigate an ever-changing world due to the COVID-19 pandemic. If you find yourself struggling with a difficult concept; stressed over politics or health; slowed by monopolistic internet providers; or annoyed at a classmate, please remember that they might feel similar. Maybe not in your very moment, but certainly recently or soon. Some of you may find the return to hybrid teaching conducive to your style of learning and personality. Others may find it stressful or difficult. These are all normal reactions. Please have compassion and empathy, and assume that everyone is doing their best.
If you find yourself having trouble learning in class, please do not hesitate to let me or Haotian Zhu know. Our goal is to make this class a bright spot in these unprecedented times, and to do whatever we can to promote a healthy learning environment for all.
All deadlines and meeting times for this class are in "Pacific Time". Note that we will be moving the clocks back one hour on Sunday November 1. For the first part of this quarter, "Pacific Time" is UTC-7. After November 1, "Pacific Time" will be UTC-8. If you are in a part of the world that doesn't change the clocks twice a year or if your change is at a different time, please be aware that the time of day for classes & deadlines in your timezone will change on Nov 1.
As per the policy above, all communication outside of the classroom should take place on Canvas. You can expect responses from teaching staff within 48 hours, but only during normal business hours, and excluding weekends.
N.B.: while CLMS students have a private Slack channel, I strongly encourage questions concerning course content and assignments to be posted to the Canvas discussion board, for two reasons. (i) Teaching staff will not look at Slack, so misinformation can spread. (ii) Not every student in the course is in the CLMS program, but they deserve to be included in course discussions and likely have many of the same questions.
Washington state law requires that UW develop a policy for accommodation of student absences or significant hardship due to reasons of faith or conscience, or for organized religious activities. The UW’s policy, including more information about how to request an accommodation, is available at Religious Accommodations Policy (https://registrar.washington.edu/staffandfaculty/religious-accommodations-policy/). Accommodations must be requested within the first two weeks of this course using the Religious Accommodations Request form (https://registrar.washington.edu/students/religious-accommodations-request/).
Your experience in this class is important to me. If you have already established accommodations with Disability Resources for Students (DRS), please communicate your approved accommodations to me at your earliest convenience so we can discuss your needs in this course.
If you have not yet established services through DRS, but have a temporary health condition or permanent disability that requires accommodations (conditions include but not limited to; mental health, attention-related, learning, vision, hearing, physical or health impacts), you are welcome to contact DRS at 206-543-8924 or email@example.com or disability.uw.edu. DRS offers resources and coordinates reasonable accommodations for students with disabilities and/or temporary health conditions. Reasonable accommodations are established through an interactive process between you, your instructor(s) and DRS. It is the policy and practice of the University of Washington to create inclusive and accessible learning environments consistent with federal and state law.
Call SafeCampus at 206-685-7233 anytime – no matter where you work or study – to anonymously discuss safety and well-being concerns for yourself or others. SafeCampus’s team of caring professionals will provide individualized support, while discussing short- and long-term solutions and connecting you with additional resources when requested.
|Date||Topics + Slides||Jurafsky & Martin||Additional Readings||Assignment out|
|Sept 29||Introduction; Syntax||Chapter 1, 12||Patas and Condor||HW1 [slides]
Due Oct 6
|Oct 4||CFGs and Parsing||Chapter 12, 13.1-13.3|
|Oct 6||CKY; CNF||Chapter 13.4.1||HW2 [slides]
|Oct 11||Parsing: CKY||Chapter 13.4.1; 14.1|
|Oct 13||PCFGs: Algorithms and Evaluation
|Chapter 14.1-14.3; 14.7
|Oct 18||PCFGs: issues and improvement||Chapter 14.4 - 14.6|
|Oct 20||Dependency Parsing||Chapter 12.7
SLP 3: Chapter 15
de Marneffe et al, 2006
McDonald et al, 2005
|Oct 25||Dependency Parsing (cont'd) + Features||Chapter 15-15.4
SLP 3: Chapter 15
|Oct 27||Semantics Intro||Chapter 17||HW4 [slides, notes]
Due Nov 3
|Nov 1||Semantics (cont'd)||Chapter 15.5-15.7; 17, 18|
|Nov 3||More Lambda Calculus
|Chapter 18.2||Blackburn & Bos, 1999, 2.3–2.4||HW5 [slides]
Due Nov 10
|Nov 8||Distributional semantics, I||Chapter 19.1-19.3, 20.1-20.4, 20.7, 20.10||Animacy practice solution|
|Nov 10||Distributional semantics, II||Chapter 20||The Illustrated word2vec||HW6 [slides]
Due Nov 17
|Nov 15||Thesaurus similarity for WSD||Chapter 19.4, 20.6, 20.9, 20.10||Resnik WSD, esp. Sec 5.1|
|Nov 17||Semantic Role Labeling||Chapter 19.4, 20.4; 21.0||Jurafsky & Gildea, 2002, pp. 1-19.||HW7 [slides]
Due Nov 24
|Nov 22||Discourse: Reference||Chapter 21.4-21.8|
|Nov 24||No Class|
|Nov 29||Discourse: Structure||Chapter 21.1-21.3|
|Dec 1||Discourse: Reference||Chapter 21; SLP3 ch 22||HW8 [slides]
Due Dec 8
|Dec 6||Wrap-up (I): case study + current papers|
|Dec 8||Wrap-up (II): semi-supervised learning + summary||HW9 [slides]
Due Dec 15