From Natural Language to Data Science

Course codes: COMP 345 & LING 345 (Winter 2026)
Instructor: Gaurav Kamath [Office Hours: Thursday 12:00-13:00, Rm 304, 1085 Av. Dr. Penfield] [Email: gaurav<dot>kamath<at>mcgill<dot>ca]
- Note: Please add the [NL2DS] tag to any email subject line, to help your instructor respond to you more quickly.
Teaching Assistants:
- Jay Gala [jay<dot>gala<at>mila<dot>quebec]
- Fengyuan Liu [fengyuan<dot>liu<at>mila<dot>quebec]
- Jessica Ojo [jessica<dot>ojo<at>mail<dot>mcgill<dot>ca]
- Mehar Bhatia [mehar<dot>bhatia<at>mila<dot>quebec]
- Fahad Amik [fahad<dot>amik<at>mail<dot>mcgill<dot>ca]
Classroom: McConnell Engineering Building 204
Time: Tuesdays and Thursdays, 10:05 am – 11:25 am
Links:
- MyCourses: announcements, slides, lecture recordings
- Slack: assignment discussions, general questions

Description

Course Format: The course format is in person unless notified. But lecture recordings will be available on MyCourses.

The last decades have seen phenomenal increases in our scientific and engineering understanding of language from a computational perspective. A large part of this success has been the rapid and unprecedented expansion of different kinds of language data as well as new computational tools for dealing with this data. This course provides an introduction to the data science of language. The emphasis will be on learning basic tools for working with language data for both engineering and scientific applications.

Goals

The goal of this course is to learn how to think about language data (predominantly raw text) and to work with it computationally. Along the way, we will learn a number of mathematical and computational tools for data collection, representation, processing, modeling, and analysis. The main emphasis of the course will be on transferring theory into practice. By the end of the course, you will know how to process large amounts of text, study the nature of words, search for information, examine statistical relationships between linguistic data, and apply these tools to study scientific questions about language. And, hopefully, along the way, you’ll also just have fun :)

Students will

Learn how to process text data using Python.
Learn the fundamentals of data science, including different statistical models.
Learn how to analyze text data using these statistical methods.
Learn how to build simple models of language domains.
Learn how to predict outcomes based on text.
Learn about the biases of current NLP systems and their implications.

Prerequisites

Required: Programming background at the level of COMP 202 or equivalent.

Recommended: Programming background at the level of COMP 250 or higher. Mathematics background at the level of MATH 240. Basic calculus and linear algebra will be helpful but not critical.

Grading

Note that the details below are subject to change.

Midterm Exam (25%)
Final Exam (25%)
Problem Sets (50%): 4 problem sets equally weighted (12.5% each).

Why does a course like this have exams? AI tools are increasingly integrated into coding interfaces, and how we write code more generally. This is mostly a good thing: tools like Copilot or ChatGPT can make us drastically more productive, and even offer personalized help when learning to code. But it’s still important that you understand the fundamentals yourself, to understand whether a coding agent is implementing what you actually want/need, and to distinguish between good and bad AI-generated code. Unfortunately, in-person exams are the most straightforward way of testing these fundamentals in a way that can’t be gamed using AI tools.

What will the exams be like? They will be multiple-choice, won’t be hard, and won’t be designed to contain any trick questions. The idea is simple: if you show up to class regularly, and understand how to implement the code through this course, you should find them extremely easy. If you never show up to class, and completely outsource all coding to AI tools, they’ll be hard.

Schedule

Lecture	Date	Topic	Notes
1	Jan 6	Introduction
2	Jan 8	Tokenization, Regular Expressions & Syntactic Parses
3	Jan 13	Keywords & Association Metrics
4	Jan 15	Classification & Regression Models	Assignment 1 Released
5	Jan 20	Classification & Regression Models	Add or drop deadline
6	Jan 22	Classification & Regression Models
7	Jan 27	Classification & Regression Models
8	Jan 29	Neural Nets	Assignment 1 Due Assignment 2 Released
9	Feb 3	Vector Representations of Words, Sentences & Documents
10	Feb 5	Vector Representations of Words, Sentences & Documents
11	Feb 10	Vector Representations of Words, Sentences & Documents
12	Feb 12	Language Modelling
13	Feb 17	Language Modelling
14	Feb 19	Language Modelling	Assignment 2 Due Assignment 3 Released
15	Feb 24	Recap Class
16	Feb 26	Midterm Exam
17	Mar 3	Reading week (No Class)
18	Mar 5	Reading week (No Class)
19	Mar 10	Decision Trees & Random Forests
20	Mar 12	Unsupervised Learning Algorithms
21	Mar 17	Unsupervised Learning Algorithms
22	Mar 19	Unsupervised Learning Algorithms
23	Mar 24	Information Theory	Assignment 3 Due Assignment 4 Released
24	Mar 26	Statistical Hypothesis Testing
25	Mar 31	Ethics & Bias
26	Apr 2	Multilingual NLP
27	Apr 7	Digital Humanities & Computational Social Sciences
28	Apr 9	Recap Class (Final Class)
29	Apr 14	No Class (as per McGill Academic Calendar)	Assignment 4 Due

Generative AI Policy

You may use any Generative AI tool (e.g., ChatGPT, GitHub Copilot, Claude) that helps you better engage with the content of the course, as long as you (i) use them to better engage with course materials, rather than using them do all of your assignments for you; and (ii) declare what tools you used, where you used them, and what you used them for.

Feel free to use any AI tools to:

Help yourself understand and debug code.
Write / auto-complete small portions of code.
Dig deeper on any of the topics covered in class.

But you may NOT:

Use AI tools to write whole assignments or code files for you.
Submit AI-generated prose in your assignments.
Use AI tools without citing them in your assignment.

Inappropriate use of Generative AI may result in penalties on grades or referral to disciplinary authorities. (You’ll also just struggle on the exams if you try to completely outsource assignments to AI tools.) If you have any question about appropriate use of AI applications for course work, please contact the instructor during his office hours.

Language of Submission

In accord with McGill University’s Charter of Students’ Rights, students in this course have the right to submit in English or in French any written work that is to be graded.

Academic Integrity

McGill University values academic integrity. Therefore, all students must understand the meaning and consequences of cheating, plagiarism and other academic offences under the Code of Student Conduct and Disciplinary Procedures (see www.mcgill.ca/students/srr/honest/ for more information)

Inclusivity

As the instructor of this course I endeavor to provide an inclusive learning environment. However, if you experience barriers to learning in this course, do not hesitate to discuss them with me or the Office for Students with Disabilities.

Extraordinary Circumstances

In the event of extraordinary circumstances beyond the control of McGill University, assessment tasks in a course are subject to change, provided students are sent adequate and timely communications regarding the change.

Territory Acknowledgment

McGill University is on land which has long served as a site of meeting and exchange amongst Indigenous peoples, including the Haudenosaunee and Anishinabeg nations. This history remains relevant to this day, particularly in terms of the current state of Indigenous languages. And since COMP / LING 345 is about computational approaches to language, it’s also specifically relevant to our course. I’m trying to organize a guest lecture on some of the language technology work being done in Canada for Indigenous languages: more to come!