Course Description

The application of neural network methods - under the name Deep Learning - has led to breakthroughs in a wide range of fields, including in building language technologies (e.g. for search, translation, text input prediction). This course will provide a hands-on introduction to the use of deep learning methods for processing natural language. Methods to be covered include static word embeddings, feed-forward networks for text, recurrent neural networks, transformers, pre-training and transfer learning, with applications including sentiment analysis, translation, and generation.

Days Time Location
Monday and Wednesday 1:00 - 2:20 PM MGH 242
see Canvas for Zoom link

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.

Teaching Staff

Role Name Office Office Hours
Instructor C.M. Downey Zoom (see Canvas for link)
in-person (GUG 407)
Monday 2:30-3:30
Tuesday 11:00-12:00
Teaching Assistant Yuanhe Tian Zoom (see Canvas for link)
in-person (GUG CompLing Treehouse)
Wednesday 3:00-4:00
Friday 11:00-12:00 (Zoom only)

Recommended Textbooks

While relevant readings are posted in the schedule below, the following are very good general resources. Names that are used to refer to these works are included in parentheses.

Prerequisites

  • Programming in Python
  • Linux/Unix commands
  • Calculus 1
  • Knowledge of vectors and matrices

Course Resources

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.

Policies

Unless explicitly mentioned below, the shared policies of the LING 57x course series apply to this course. Please read those policies for more information.

As we continue to navigate health crises and troubling world events, stress and anxiety are at all-time highs. If you find yourself struggling with a difficult concept; stressed over politics or health; or annoyed at a classmate, please remember that they feel similar. Maybe not in your very moment, but certainly recently or soon. Some of you may find remote learning particularly conducive to your style of learning and personality. Others will find it difficult to concentrate and maintain enthusiasm. These are all normal reactions.

If you find yourself having trouble learning in class, please do not hesitate to let one of us 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.

A note on time zones

All deadlines and meeting times for this class are in "Pacific Time". Now that we are in Daylight Savings Time, this is UTC-7.

Grading

  • 100%: Homework Assignments
  • Up to 2% adjustment for significant in-class or discussion participation

Communication

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.

Religious Accommodation

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/).

Access and Accommodations

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 uwdrs@uw.edu 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.

Safety

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.

Schedule


Date Topics + Slides Readings Events
March 27 Introduction / Overview; History
March 29 Linear Algebra Essence of Linear Algebra Ch.1-8 HW1 out
[pdf, tex, slides]
[due April 6]
April 3 Word vectors; Gradient descent JM 5.4-5.6, 6
YG 2
April 5 Word2Vec JM 6.8 - 6.12 HW2 out
[pdf, tex, slides]
[due April 13]
April 10 Neural Networks
edugrad library
JM 7.1 - 7.4
YG 4
April 12 Computation graphs; Backpropagation JM 7.6.3 - 7.6.5
YG 5.1.1 - 5.1.2
GBC 6.5

Calculus on computational graphs
CS 231n notes 1
CS 231n notes 2 (vector/tensor derivatives)
Yes, you should understand backprop
HW3 out
[pdf, tex, slides]
[due April 20]
April 17 Feed-forward networks for LM and classification JM 7.5
YG 9

A Neural Probabilistic Language Model (Bengio et al 2003)
Deep Unordered Composition Rivals Syntactic Methods for Text Classification (Iyyer et al 2015)
April 19 Recurrent neural networks JM 9.1-9.5

The Unreasonable Effectiveness of Recurrent Neural Networks
HW4 out
[pdf, tex, slides]
[due April 27]
April 24 Vanishing gradients; RNN variants JM 9.6
YG 15

Understanding LSTMs
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
On the difficulty of training recurrent neural networks
April 26 Sequence-to-sequence; Attention JM 10

Sequence to Sequence Learning with Neural Networks (original seq2seq paper)
Neural Machine Translation by Jointly Learning to Align and Translate (original seq2seq + attention paper)
HW5 out
[pdf, tex]
[due May 4]
May 1 Transformers 1 JM 9.7-9.9

Attention is All You Need (original Transformer paper)
The Annotated Transformer
The Illustrated Transformer
May 3 Transformers 2 " HW6 out
[pdf, tex]
[due May 11]
May 8 Pre-training / Fine-tuning Paradigm JM 11
Contextual Word Representations: Putting Words into Computers
The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)
May 10 Pre-training / fine-tuning paradigm (cont.) " HW7 out
[pdf, tex]
[due May 18]
May 15 Interpretability and Analysis Analysis Methods in Natural Language Processing
A Primer in BERTology
May 17 Multilingual NLP Cross-Lingual Language Model Pretraining

Optional / peruse if interested:
Are All Languages Created Equal in Multilingual BERT?
Emerging Cross-lingual Structure in Pretrained Language Models
On the Cross-lingual Transferability of Monolingual Representations
Word Translation Without Parallel Data
Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining
HW8 out
[pdf, tex]
[due May 25]
May 22 Bonus topic: Neural Networks for Speech Signal Processing
Guest lecturer: Matt Kelley
JM 16
May 24 Overflow / Summary / Review HW9 out
[pdf, tex]
[due June 1]
May 29 Memorial Day: No Class
May 31 No Class (finished ahead of schedule)