This course introduces the theoretical foundations and practical methods of Natural Language Processing (NLP). Students will learn how machines process and understand human language, beginning with linguistic and statistical foundations, progressing through traditional machine learning approaches, and culminating in modern deep learning techniques including transformers and large language models (LLMs). The course also addresses evaluation, bias, fairness, and responsible NLP.
Books
Speech and Language Processing, Daniel Jurafski and James Martin, 3rd edition, 2026
Learning Outcomes
By the end of the course, students will be able to:
- Explain core linguistic and statistical concepts underlying NLP
- Implement and evaluate traditional and neural NLP models
- Understand and compare major NLP tasks and benchmarks
- Describe transformer architectures and LLMs
- Critically analyze bias, ethics, and societal impact in NLP systems
Instructor
Aya Zirikly
Office hours:
Tuesday 3:15-4:15, classroom or SEH 2880
Meeting
Time: Every Tuesday 12:45PM - 03:15PM
01/13/2026 - 04/21/2026 (excluding Tuesday 03/10/2026 Spring break)
1957 E 111, Foggy Bottom Campus
Grading -tentative
- Homeworks 20%
- Quiz + midterm 35%
- Project 40%
- Participation 5%
GW University Policies
Please check the university policies