Class Time: Mondays and Wednesdays 10:10am-11:25am

Location: 152 HORACE MANN (Teachers College)

**Instructor: Smaranda Muresan**

smara601.jpeg

Office: 901 Milstein (Barnard Campus)

Office hours: Monday 1:00-2:00pm

Email: [email protected]

TAs:

Nick Deas

image.png

Office: CEPSR 724 (Columbia University)

Office hours: Tue and Thursdays 2-3pm

Email: [email protected]

Anubhav Jangra

anubhav.jpg

Office: Milstein 911A (Barnard College)

Office Hours: Mon and Wed 2-3pm

Email: [email protected]

https://mail.google.com/mail/u/1/images/cleardot.gif

**Arkadiy Saakyan**

me.jpg

Office: Milstein 911A (Barnard College)

Office Hours: Thursday 5-7pm

Email: [email protected]

https://mail.google.com/mail/u/1/images/cleardot.gif

https://mail.google.com/mail/u/1/images/cleardot.gif

📜 Course Description (Jump to Course Schedule)

This course provides an introduction to the field of Natural Language Processing (NLP) at an undergraduate level. We will discuss properties of human language at different levels of representation (morphology, syntax, semantics, pragmatics), and will learn how to create systems that can analyze, understand, and generate natural language. We will study machine learning methods used in NLP such as various forms of Neural networks and will focus particularly on conceptual and technical advances of frontier Large Language Models based NLP technologies (think ChatGPT) that are revolutionizing classical computational linguistics and NLP fields. We will also discuss applications such as question answering, summarization, language generation and as well as data, benchmarks and evaluation frameworks. We will discuss ethical aspects of NLP research and applications. Homework assignments will consist of programming projects in Python. Class will also have a midterm and a mini final project instead of a final exam.

Prerequisite(s): COMS W3134 or W3136 or W3137 (or equivalent). Background in probability/statistics and linear algebra is also required and experience with Python programming is strongly encouraged. Some previous or concurrent exposure to AI and machine learning is beneficial, but not required.

Announcements

<aside> 💡 [Due 09/07/2024 11:59pm EST] Please make sure you fill in the **Class Survey.** tIf you already did when registering for the class no need to do it again, it is the same survey.

</aside>

🗓 Course Schedule

Some topics/readings might be subject to change

Untitled

🏆 Coursework and Grading

:

Assignments (40%)

There will be 4 assignments for the class, you can drop the lowest scoring one from consideration of the grade.