Syllabus Application
Natural Language Processing
CS 445
Faculty:
Faculty of Engineering and Natural Sciences
Semester:
Fall 2025-2026
Course:
Natural Language Processing - CS 445
Classroom:
FASS-G062
Level of course:
Undergraduate
Course Credits:
SU Credit:3.000, 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).