Natural Language Processing

ETH Zürich, Fall 2024: Course catalog

Course Description

The course constitutes an introduction to modern techniques in the field of natural language processing (NLP). Our primary focus is on the algorithmic aspects of structured NLP models. The course is self-contained and designed to complement other machine learning courses at ETH Zürich, e.g., Deep Learning (263-3210-00L) and Advanced Machine Learning (252-0535-00L). At some points in the course, familiarity with advanced algorithms, e.g., the contents of Algorithms Lab (263-0006-00L), and mathematical statistics, e.g., the contents of Fundamentals of Mathematical Statistics (401-3621-00L), will be useful. However, the necessary background knowledge can certainly be picked up in the context of the course, i.e., neither of the above-listed courses is a hard prerequisite. The course also has a strong focus on algebraic methods, e.g., semiring theory. In addition to machine learning, we also cover the linguistic background necessary for reading the NLP literature.

News

13.09.2024   Class website is online!
18.09.2024   Exercises and solutions published!
23.09.2024   First assignments batch published! Assignment 1, Assignment 2, Assignment 3
11.11.2024   Second assignments batch published! Assignment 4, Assignment 5, Assignment 6

Organisation

On the Use of Class Time

There are two lecture slots for NLP. The first slot is on Monday from 12h to 14h. During this time, the main lecture will be given. The second slot is on Tuesday from 13h to 14h and will be used as a spill-over time if we did not get through all of the lecture material on Monday (this ensures that the class stays on track) and, time-permitting, the professor will work examples and hold an open-ended ask-me-anything-about-NLP session.

Both lectures will be given in the lecture hall HG F1 and live broadcast on Zoom; the password is available on the course Moodle page.

Lectures will be recorded. You can find the links to the recordings on the course Moodle page.

Important: The ETH semester starts on Tuesday, September 17th. This is when the first lecture will take place.

Live Chat

In addition to class time, there will also be a RocketChat-based live chat hosted on ETH’s servers. Students are free to ask questions of the teaching staff and of others in public or private (direct message). There are specific channels for each of the 6 assignments as well as for reporting errata in the course notes. All data from the chat will be deleted from ETH servers at the course’s conclusion. The chat supports LaTeX for easier discussion of technical material.

Important: There are a few important points you should keep in mind about the course live chat:

  1. RocketChat will be the main communications hub for the course. You are responsible for receiving all messages broadcast in the RocketChat.
  2. Your username should be firstname.lastname. This is required as we will only allow enrolled students to participate in the chat and we will remove users which we cannot validate.
  3. Tag your questions as described in the document on How to use Rycolab Course RocketChat channels. The document also contains other general remarks about the use of RocketChat.
  4. Search for answers in the appropriate channels before posting a new question.
  5. Ask questions on public channels as much as possible.
  6. Answer to posts in threads.
  7. The chat supports LaTeX for easier discussion of technical material. See How to use LaTeX in RocketChat.
  8. We highly recommend you download the desktop app here.

This is the link to the main channel. To make the moderation of the chat more easily manageable, we have created a number of other channels on RocketChat. The full list is:

If you feel like you would benefit from any other channel, feel free to suggest it to the teaching team!

Course Notes

We are currently working on turning out class content into a book! The current draft of the book, i.e., the course notes, can be found here. Please report all errata to the teaching staff; we created an errata channel in RocketChat.

Other useful literature:

Grading

Marks for the course will be determined by the following formula:

  • 70% Final Exam
  • 30% Assignment or Class Project

On the Final Exam

The final exam is comprehensive and should be assumed to cover all the material in the slides and class notes. About 50% of exam questions will be very similar (or even identical) to the theory portion of the class assignments. Thus, it behooves you to at least look at all the assignment questions while preparing for the final exam even if you do not turn them all in for a grade. Solutions for the assignments will not be provided (they will be re-used every year), but the teaching staff can answer questions if you solve the problems ahead of time.

On the Class Assignments

There will be 6 assignments which will be released (in their final form) roughly every two weeks. We impose three firm deadlines for handing in your solutions:

  • Assignment 1, 2, 3: December 15th
  • Assignments 4, 5, and 6: January 15th

Only your highest-scoring 4 assignments will count towards your grade; each will be weighted equally. So, in principle, you may opt to not turn in 2 out of the 6 assignments without any effect on your grade. Note: Even though we plan to grade your submissions within one month, we advise you not to wait for your grades to be returned before you decide to tackle the next assignments. In essence, do not base your submission strategy on our grading estimates! The assignments will be graded according to the pre-determined Assignment grading rubric.

The class assignments were crafted to dovetail nicely with the lecture contents and, moreover, to complement the lectures through a more hands-on approach to the material. Each assignment has a theory portion, which will generally involve derivations or proofs related to the material, and a coding portion where you will implement a working model for one of the NLP tasks discussed in the lecture. The theory and the coding halves of the assignments will be weighted equally.

Assignment sheets:

The code relating to some of the assignments will be published on the public github repository. You should fork the repository and pull the incoming changes whenever they are released.

Very important: We require the solutions to be properly typeset. Handwritten solutions will not be accepted. We recommend using LaTeX (with Overleaf), but markdown files with MathJax for the mathematical expressions are also fine. We provide a template for the writeups here; however, feel free to use your own.

Additionally, the solutions have to be presented in a clean and readable way, with all sub-steps of the solutions presented in a logical order. Note that this does not mean that your submissions have to be overly verbose and long. It simply means that you should explain your reasoning and the steps of your solutions in a clear and concise way. To encourage this, we will, for every assignment, award 2 additional points for properly explained and formatted solutions.

The detailed instructions for the submission will be given in each assignment separately, but the submissions will always be through the course Moodle page. The submission links are:

On the Tutorials

Tutorials will take place Wednesdays 16h to 19h in HG F7 and on Zoom (same link as the lectures). Their main purpose will be to solve some exercises with you that will help you grasp the concepts from the lecture and to help you prepare for the exam. They will also introduce new assignments and allow you to ask questions about them. Roughly, we expect to devote 2 hours per week to exercises and 1 hour to the assignments (when a new assignment has been released). We therefore strongly encourage you to look at the assignment problems in due time and come to the discussions sessions with your questions. We want the sessions to be useful for you!

Assignment Office Hours

In addition to the Tutorials, we will hold assignment-specific online office hours on Zoom about 2 weeks after the assignment has been introduced. You will have the opportunity to talk to the TAs responsible for that assignment and ask individual questions you do not want to discuss on a public RocketChat channel. We will send out 10 minute slots for you to sign up for closer to the time on the corresponding assignment RocketChat channels.

On the Class Project

It is highly recommended that you do the class assignments. However, students may choose to do a course project (in groups of up to 4 people) in lieu of the class assignments. This option is only recommended for academically oriented students who are interested in using this course to get into NLP research. If you choose to do a class project, you must submit a project proposal by October 31, 2024, on Moodle. The proposal is ungraded and will be inspected by the teaching assistants to ensure that the project is doable and you will pass the course should you execute the project as proposed. The write-up and code for the final project are due January 15, 2025; it is to be submitted through Moodle. General guidelines for the class project are given here.

Project work submission will be done on the course Moodle page. The submission links are:

Syllabus

Week Date   Topic Slides   Readings Supplementary Material Material Exercise Sheets
1 17.9.2024 Introduction to NLP, Course logistics,
Introduction of the TA team
Lecture 1 Eisenstein Ch. 1
2 23.9.2024 Backpropagation Lecture 2 Goodfellow, Bengio and Courville Ch. 6.5 Chris Olah's Blog
Justin Domke’s Notes
Tim Vieira’s Blog
Moritz Hardt’s Notes
Bauer (1974)
Baur and Strassen (1983)
Griewank and Walter (2008)
Eisner (2016)
Backpropagation Proof
Computation Graph for MLP
Computation Graph Example
Week 2 Exercises
Week 2 Solutions
24.9.2024 Backpropagation
3 30.9.2024 Log-Linear Modeling---Meet the Softmax Lecture 3 Eisenstein Ch. 2 Ferraro and Eisner (2013)
Jason Eisner’s list of further resources on log-linear modeling
Week 3 Exercises
Week 3 Solutions
1.10.2024 Log-Linear Modeling---Meet the Softmax
4 7.10.2024 Sentiment Analysis with Multi-layer Perceptrons Lecture 4 Eisenstein Ch. 3 and 4;
Goodfellow, Bengio and Courville Ch. 6
Week 4 Exercises
Week 4 Solutions
8.10.2024 Sentiment Analysis with Multi-layer Perceptrons
5 14.10.2024 Language Modeling with n-grams and LSTMs Lecture 5 Eisenstein Ch. 6;
Goodfellow, Bengio and Courville Ch. 10
Good Tutorial on n-gram smoothing
Good–Turing Smoothing
Kneser and Ney (1995)
Bengio et al. (2003)
Mikolov et al. (2010)
Week 5 Exercises
Week 5 Solutions
15.10.2024 Language Modeling with n-grams and LSTMs
6 21.10.2024 Part-of-Speech Tagging with CRFs Lecture 6 Eisenstein Ch. 7 and 8 Tim Vieira's Blog
McCallum et al. (2000)
Lafferty et al. (2001)
Sutton and McCallum (2011)
Koller and Friedman (2009)
Week 6 Exercises
Week 6 Solutions
22.10.2024 Part-of-Speech Tagging with CRFs, Assignment 2 introduction
7 28.10.2024 Transliteration with WFSTs Lecture 7 Eisenstein Ch. 9 AFLT Course Notes Chapters 1, 2, and 3
Knight and Graehl (1998)
Mohri, Pereira and Riley (2008)
Week 7 Exercises
Week 7 Solutions
29.10.2024 Transliteration with WFSTs
8 4.11.2024 Cancelled
5.11.2024 Cancelled
9 11.11.2024 Context-Free Parsing with CKY Lecture 8 Eisenstein Ch. 10 The Inside-Outside Algorithm
Jason Eisner’s Slides
Kasami (1966)
Younger (1967)
Cocke and Schwartz (1970)
Week 8 Exercises
Week 8 Solutions
12.11.2024 No Q&A Session
10 18.11.2024 No Lecture
19.11.2024 Dependency Parsing with the Matrix-Tree Theorem Lecture 9 (last year) Eisenstein Ch. 11 Koo et al. (2007)
Smith and Smith (2007)
McDonald and Satta (2007)
McDonald, Kübler and Nivre (2009)
Week 9 Exercises
Week 9 Solutions
11 25.11.2024 Semantic Parsing with CCGs Lecture 10 (last year) Eisenstein Ch. 9.3 and 12 Weir and Joshi (1988)
Kuhlmann and Satta (2014)
Mark Steedman's CCG slides
Week 10 Exercises
Week 10 Solutions
26.11.2024 Semantic Parsing with CCGs
12 2.12.2024 Machine Translation with Transformers Lecture 11 (last year) Eisenstein Ch. 18 Vaswani et al. (2017)
The Annotated Transformer
The Illustrated Transformer
The Transformer Family
Week 11 Exercises
Week 11 Solutions
3.12.2024 Machine Translation with Transformers
13 9.12.2024 Axes of Modeling Lecture 12 (last year) Review Eisenstein Ch. 2;
Goodfellow, Bengio and Courville Ch. 5 and 11
Week 12 Exercises
Week 12 Solutions
10.12.2024 Axes of Modeling
14 16.12.2024 Bias and Fairness in NLP Lecture 13 (last year) Bolukabasi et al. (2016)
Gonen and Goldberg (2019)
Hall Maudslay et al. (2019)
Vargas and Cotterell (2020)
A Course in Machine Learning Chapter 8
17.12.2024 Bias and Fairness in NLP

Tutorial Schedule

Week Date   Topic Teaching Assistant Material
1 18.9.2024 No Tutorial
2 25.9.2024 No tutorial
3 2.10.2024 Backpropagation, Assignment 1 introduction Niklas Stoehr, Nazar Puriy Puriy
4 9.10.2024 Log-Linear Modeling Anej Svete
5 16.10.2024 Sentiment Classification with Multi-layer Perceptrons Manuel de Prada Corral
6 23.10.2024 Language Modeling with n-grams and LSTMs Nazar Puriy Puriy
7 30.10.2024 Part-of-speech Tagging with CRFs, Assignment 2 introduction Yahya Emara, Anej Svete, Manuel de Prada Corral
8 6.11.2024 Transliteration with WFSTs, Assignment 3 introduction Vasiliki Xefteri
9 13.11.2024 No Tutorial
10 20.11.2024 Context-free Parsing, Assignment 4 introduction Andreas Opedal, Yahya Emara
11 27.11.2024 Dependency Parsing, Assignment 5 introduction Tianyu Liu, Aidyn Ubingazhibov
12 4.12.2024 Semantic Parsing Alexandra Butoi
13 11.12.2024 Machine Translation with Transformers, Assignment 6 introduction Aayush Grover, Aidyn Ubingazhibov
14 18.12.2024 Axes of Modeling, Assignment 6 office hours Aayush Grover