CS 6120: Natural Language Processing

Course Details

The knowledge coverage will be the same for sessions 21600 and 21601, but the lecture slides will differ. Please attend the lecture you are enrolled in.

Course description

Welcome! This is a graduate-level course on Natural Language Processing (NLP). This class introduces both foundational and modern language technologies, as well as their applications. We will begin with early statistical models, such as Naive Bayes and logistic regression, and progress to modern large language models. Along the way, we will explore a variety of core NLP tasks, such as summarization, classification, and machine translation, as well as some basic linguistic concepts.

The course will also cover different evaluation methods and commonly used metrics, as well as NLP applications in the social sciences and humanities. Beyond these, we will explore some emerging research areas such as multimodal NLP (language and vision), privacy and ethical challenges of deploying language technologies.

The goal of this class is twofold: first, to provide students with the knowledge and skills to understand and deploy language technologies; and second, to encourage a deeper appreciation of language itself and the societal implications of language technologies.

Location:

Time:

Grading:

Complete independently: 5 programming assignments (30%), 5 quizzes (30%)

Complete in groups of 1-4:
Course project (40%): initial pitch 5%, data and experimental design 5%, grade contract 2%, presentation 3%, final report 25%

Textbook:

Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition. Online manuscript released August 24, 2025. (Draft chapters available online)

Gradescope: code to join NGZDZP

Ed Discussion: link to join

Course Staff

Instructors:

Session 21600: David Smith, email: dasmith[at]ccs.neu.edu

Session 21601: Si Wu, email: siwu[at]ccs.neu.edu

TAs:

Divya Sri Bandaru, email: bandaru.di[at]northeastern[dot]edu

Tejus Dinesh, email: dinesh.te[at]northeastern[dot]edu

Zankhana Pratik Mehta, email: mehta.zan[at]northeastern[dot]edu

Office hours:

Policies

Quiz

Coding assignment late policy

Assignments are due at the announced due date and time, usually 11:59 p.m. You will be granted one homework extension of four calendar days, to be used at your discretion, without having to ask. This single extension is meant to smooth over unforeseen crunches in your schedule, and you cannot simply distribute the four late days among four assignments. After the first late assignment, unexcused late assignments will be penalized 10% per calendar day late. We normally will not accept assignments after the date on which the following assignment is due or after the solutions have been handed out, whichever comes first. If you know in advance of circumstances that would cause you to turn in an assignment late, please contact the instructor before the assignment is due to ask if an extension is possible.

Academic Integrity policy

Please refers to the Academic Integrity Policy here.

Disability Access Services

We are committed to accommodating students with disabilities. Please contact Disability Access Services and follow the outlined procedure.

Final Grade

>93% A, 90-93% A-, >87 B+, >83-87% B, 80-83% B-, >77 C+, >73-77% C, 70-73% C-, >67 D+, >63-67 D, 60-63 D-, less than 60% F.

Guest Lectures

Guest lectures will be recorded and posted on Ed afterward. Students are encouraged to attend in-person to engage with the guest lecturers.

Schedule