Syllabus Application
CS 445
Natural Language Processing
Faculty
Faculty of Engineering and Natural Sciences
Semester
Spring 2025-2026
Course
CS 445 -
Natural Language Processing
Time/Place
Time
Week Day
Place
Date
12:40-14:30
Mon
FENS-L045
Feb 16-May 22, 2026
16:40-17:30
Wed
FENS-L045
Feb 16-May 22, 2026
Level of course
Undergraduate
Course Credits
SU Credit:3, ECTS:6, Engineering:6
Prerequisites
CS 204 and ( CS 210 or DSA 210)
Corequisites
-
Course Type
Lecture
Instructor(s) Information
Dilara Keküllüoğlu
Course Information
Catalog Course Description
This course studies the theory, design and implementation of natural language processing systems. Topics include text processing, regular expressions, statistical properties of text, edit distance, language modeling, text classification, sequence modeling, topic modeling, computational morphology, neural networks for NLP, chatbots, transfer learning for NLP.
Course Learning Outcomes:
| 1. | To describe the statistical properties of text in natural language. |
|---|---|
| 2. | To implement programs that can process textual data and extract valuable information from it. |
| 3. | To apply well-known language processing techniques to text. |
| 4. | To explain the significance and principles of language modeling. |
| 5. | To develop machine learning models to classify documents, sub-documents or terms. |
| 6. | To assess the quality of natural language processing models applied to text. |
Course Objective
A student who succesfully fulfills the course requirements will be able to demonstrate:
1) To describe the statistical properties of text in natural language.
2) To implement programs that can process textual data and extract valuable information from it.
3) To apply well-known language processing techniques to text.
4) To explain the significance and principles of language modeling.
5) To develop machine learning models to classify documents, sub-documents or terms.
6) To assess the quality of natural language processing models applied to text.
1) To describe the statistical properties of text in natural language.
2) To implement programs that can process textual data and extract valuable information from it.
3) To apply well-known language processing techniques to text.
4) To explain the significance and principles of language modeling.
5) To develop machine learning models to classify documents, sub-documents or terms.
6) To assess the quality of natural language processing models applied to text.
Sustainable Development Goals (SDGs) Related to This Course:
| Gender Equality | |
| Industry, Innovation and Infrastructure | |
| Reduced Inequalities |
Course Materials
Resources:
Daniel Jurafsky and James H. Martin, {\textit{Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition}} (3rd edition online).