Syllabus

CS 478

Natural Language Processing (NLP)

Instructor

Antonis Anastasopoulos (antonis [at] gmu [dot] edu)

Office Hours: by appointment.

Teaching Assistant

Joshua Otten (jotten6@gmu.edu)
Office Hours: TBD

Meets

Friday, 10:30am to 1:10 PM, Exploratory Hall L102.

Course Web Page

https://nlp.cs.gmu.edu/course/cs478-fall26/.
We will use Canvas for materials distribution, Gradescope for assignment submission and grading, and Piazza for Q&A (sign up link available here (soon)).

Course Description

Massive amounts of information in our daily life are expressed in natural language. In this class, we will study building computing systems that can process, understand, and communicate in natural language. This field is called natural language processing, or NLP. This class will focus on introducing fundamental concepts in NLP, and will cover techniques and necessary programming skills for building machine learning/deep learning-based NLP models. In the last several classes, we will further study cutting-edge research problems in NLP, including large language models, agents, neural network interpretation, multilingual NLP, and so on.

Prerequisites

CS310 (Data Structures), CS330 (Formal Methods and Models), and proficiency in Python programming. Please contact the instructor if you have questions about the necessary background.

Class Format

The class will be in-person. Each class will take the following format:
  • Reading: Before the class, you will be pointed to some reading materials (see "Reading Materials" in the course schedule) . Reading is not required but highly recommended to do before the class.
  • Summary/Elaboration/Q&A: In the class, the instructor will summarize important points from the reading material, elaborating on details that were not included in the reading while fielding any questions. New material on cutting-edge methods, or a deep look into one salient method will also be covered.
  • Quiz: In some classes, there will be in-class quizzes evaluating student learning performance. The quiz will be based on the content in the previous lectures.

Grading

There will be knowledge checks along the way to assist you in engaging with the material. Your final grade will be dependent on:

Semi-Weekly Quizzes: 30%. We will have weekly (for about half of the weeks) in-class quizzes, each containing 2-3 short-answer questions covering contents introduced in previous lectures. The instructor will specify the range one class before the quiz. Each quiz question is worth 5% of the total grade.

Assignments: 50%. There will be four assignments in this class. Each assignment must be completed independently. The use of AI assistants is allowed, as will be described in each of them. Extra credits will be available in most assignments.

  • A1: Understand n-gram and neural language models (15%).
  • A2: Build a feedforward neural net for sentiment classification, expand it into a BERT-based sentiment classifier, and analyze it (15%).
  • A3: Explore Large Language Models (10%).
  • A4: Reproduce a seminal NLP paper using AI agents (10%).

Midterm: 10%. There will be a midterm exam covering 10% of your grade. Details TBD.

Final Exam: 10%. There will be a final exam covering 10% of your grade. Details TBD.

Your final letter grade will be given based on:

Letter Grade Points (out of 100)
A+ 100+ (w/ extra credits)
A 95-100
A- 90-94
B+ 85-89
B 82-84
B- 78-81
C+ 74-77
C 72-73
C- 70-71
D 60-69
F 0-59

Late Day Policy for Assignments:
In case there are unforeseen circumstances that don’t let you turn in your assignment on time, 5 late days total over the four assignments will be allowed. Notes that the late days cannot be used fractionally, e.g., submitting the assignment 1 hour late will incur 1 late day. Assignments that are late beyond the allowed late days will be graded down by 5% per day. In the case of a serious illness or other excused absence, as defined by university policies (including providing necessary evidence), coursework submissions will be accepted late by the same number of days as the excused absence. However, students should inform the instructor as soon as they can, ideally before the due date.

Class Attendance Policy:
As we will have quizzes for some classes, attendence is highly suggested. Class will not be recorded. If you miss a quiz, you lose the credits (i.e., no make ups for quiz). However, in the case of a serious illness or other excused absence, as defined by university policies (including providing necessary evidence), students will be excused and the quiz can be taken home. However, students should inform the instructor as soon as they can, before the quiz date.

Readings

Students should be able to understand the course content just by following the lecture and by doing the readings. However, the following textbooks serve as good references.
  • Jurafsky and Martin, Speech and Language Processing, 3rd edition [online; version Aug 20, 2026] (Referred to as "JM");
  • Jacob Eisenstein, Natural Language Processing [online] (Referred to as "Eisenstein");
  • Yoav Goldberg, Neural Network Methods in Natural Language Processing [publisher] [online primer pdf] (Referred to as "Goldberg-Publisher/Primer"); Note that the "publisher" version can be downloaded if you use the school VPN.

Tentative Schedule

# Date Topic Reading Materials Assignment Dates
1 08/28 Introduction, Class Outline
Text Processing and Probability Basics
JM Ch 2 Assignment 1 Out
2 09/04 Neural Network Basics JM Ch 6
3 09/11 n-gram Language Models and Basic LM Concepts JM Ch 3
4 09/18 ML/NLP Experimental Design
Language Representations
JM Ch 4 and 5 Assignment 1 Due; Assignment 2 Out
5 09/25 Transformers and Pre-training JM Ch 7
6 10/02 Post-training TBD Assignment 2 Due; Assignment 3 Out
7 10/09 Topics on Prompt-based learning and LLM Agents
8 10/16 Midterm
9 10/23 Topics on Interpretability
10 10/30 Topics on Machine Translation Assignment 3 Due; Assignment 4 Out
11 11/06 Topics on Syntax and Morphology
12 11/13 Topics on Multilinguality
13 11/20 Topics on Phonetics and Speech Processing
14 11/27 Thanksgiving Break - No Class
15 12/4 AI/NLP Ethics
Recap
Assignment 4 Due
16 12/11 Final Exam

See below for a compact schedule and (tentative) deadlines:
Project Chart

Honor Code

The class enforces the GMU Honor Code, and the more specific honor code policy special to the Department of Computer Science. You will be expected to adhere to this code and policy.

On the Use of AI Assistants

For all of the assignments in the course, as well as for in-class demos and excercises, the use of AI assistants (like Claude, ChatGPT, Gemini, etc) is allowed, if not encouraged. However, note that relying 100% on AI assistants will not lead to perfect scores, and will also impact your learning. Recent studies

Unauthorized Devices and Materials

By default, in-class assessments are closed book, closed notes, and there are no authorized devices. Policies regarding authorized material and devices will be specified per assessment. The possession of an unauthorized device or unauthorized material during any assessment will result in an automatic 0 on that assessment, even if the device or material is not used. For example, if you are asked to turn off your phone and put it away in your backpack, and then you are seen with a phone in your pocket during a quiz or exam (even if it is off), then that quiz or exam will be an automatic 0. The same rule also applies for any limited access devices or material. For example, if you are allowed some form of notes and a calculator during a quiz or exam but there are restrictions given (such as the quantity of notes, or capabilities of the calculator), and you are seen with something outside the parameters specified, then that quiz or exam will be an automatic 0. This policy is non-negotiable and it is your responsibility to confirm before the assessment if something does or does not adhere to the assessment policies.

Note to Students

Take care of yourself! As a student, you may experience a range of challenges that can interfere with learning, such as strained relationships, increased anxiety, substance use, global pandemics, feeling down, difficulty concentrating and/or lack of motivation. All of us benefit from support during times of struggle. There are many helpful resources available on campus and an important part of having a healthy life is learning how to ask for help. Asking for support sooner rather than later is almost always helpful. GMU services are available, and treatment does work. You can learn more about confidential mental health services available on campus at: https://caps.gmu.edu/. Support is always available (24/7) from Counseling and Psychological Services: 703-527-4077.

Disabilities

If you have a documented learning disability or other condition which may affect academic performance, make sure this documentation is on file with the Office of Disability Services and come talk to me about accommodations. I will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Services, I encourage you to contact them at ods@gmu.edu.

Diversity and Inclusion

GMU seeks to create a learning environment that fosters respect for people across identities. We welcome and value individuals and their differences, including gender expression and identity, race, economic status, sex, sexuality, ethnicity, national origin, first language, religion, age and ability. We encourage all members of the learning environment to engage with the material personally, but to also be open to exploring and learning from experiences different than their own. Check out the Mason Non-Discrimination Policy and the Mason Diversity statement.

Sexual or Interpersonal Violence

As a faculty member, I am designated as a “Non-Confidential Employee,” and must report all disclosures of sexual assault, sexual harassment, interpersonal violence, stalking, sexual exploitation, complicity, and retaliation to Mason’s Title IX Coordinator per University Policy 1202. If you wish to speak with someone confidentially, please contact one of Mason’s confidential resources, such as Student Support and Advocacy Center (SSAC) at 703-993-3686 or Counseling and Psychological Services (CAPS) at 703-993-2380. You may also seek assistance or support measures from Mason’s Title IX Coordinator by calling 703-993-8730, or emailing titleix@gmu.edu.

Student Privacy

Student privacy is governed by the Family Educational Rights and Privacy Act (FERPA). For this reason, students must use their Mason email account to receive important University information, including communications related to this class. I will not respond to messages sent from or send messages to a non-Mason email address.

Recording and/or sharing class materials

Some kinds of participation in online study sites violate the Mason Honor code: these include accessing exam or quiz questions for this class; accessing exam, quiz, or assignment answers for this class; uploading of any of the instructor's materials or exams; and uploading any of your own answers or finished work. Always consult your syllabus and your professor before using these sites.

Undergraduate Course Repetition

Please see AP. 1.3.4 in the University Catalog and consult with your academic advisor if you have any questions regarding repeating an undergraduate class for credit.