Information Package / Course Catalogue
Natural Language Processing With Machine Learning
Course Code: CSE431
Course Type: Area Elective
Couse Group: First Cycle (Bachelor's Degree)
Education Language: English
Work Placement: N/A
Theory: 2
Prt.: 2
Credit: 3
Lab: 0
ECTS: 6
Objectives of the Course

The main objective of this course is to make syntactic and semantical analysis of natural language by machine learning techniques. The techniques to capture the meaning in natural language will be applied in different application areas such as question answering systems, machine translation, recommender systems and chatbots.

Course Content

Introduction to Natural Language Processing. Language models. Information retrieval. Vector semantics. Deep neural network architectures for natural language processing. Syntactic, statistical, dependency, semantic parsing. Chatbots. Question answering systems. To implement mentioned topics with the help of Python programming language.

Name of Lecturer(s)
Assoc. Prof. Fatih SOYGAZİ
Learning Outcomes
1.Gaining the understanding of natural language analysis techniques with the use of rule-based approaches and statistical methods.
2.Gaining the ability to understand Language Models.
3.Gaining the understanding of syntactic and semantic techniques of natural language processing.
4.Grasping machine-translation techniques.
5.Grasping discourse analysis methods.
Recommended or Required Reading
1.Dan Jurafsky and James H. Martin; “Speech and Language Processing”, 3rd Ed., Prentice Hall, 2020.
2.Steven Bird, Ewan Klein, Edward Loper, “Natural Language Processing with Python”, 1st Ed., O’Reilly Media, 2009.
Weekly Detailed Course Contents
Week 1 - Theoretical & Practice
Introduction
Week 2 - Theoretical & Practice
Basic Text Processing
Week 3 - Theoretical & Practice
Language Models
Week 4 - Theoretical & Practice
Information Retrieval, Text Classification
Week 5 - Theoretical & Practice
Vector Semantics
Week 6 - Theoretical & Practice
Information Extraction, Named Entity Recognition, Part-of-Speech Tagging
Week 7 - Theoretical & Practice
Neural Networks and Natural Language Processing
Week 8 - Theoretical & Practice
Neural Networks and Natural Language Processing
Week 9 - Theoretical & Practice
Deep Learning Architectures for Sequence Processing
Week 10 - Theoretical & Practice
Deep Learning Architectures for Sequence Processing
Week 11 - Theoretical & Practice
Syntactic Parsing
Week 12 - Theoretical & Practice
Statistical Parsing, Dependency Parsing
Week 13 - Theoretical & Practice
Semantics
Week 14 - Theoretical & Practice
Semantic Role Labelling, Coreference Resolution
Week 15 - Theoretical & Practice
Question Answering Systems, Chatbots, Recommender Systems
Assessment Methods and Criteria
Type of AssessmentCountPercent
Midterm Examination1%40
Final Examination1%60
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140228
Lecture - Practice140228
Assignment140114
Term Project116824
Midterm Examination116824
Final Examination1161632
TOTAL WORKLOAD (hours)150
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
OÇ-1
3
3
3
3
4
3
3
4
3
3
3
OÇ-2
4
4
4
3
5
4
3
4
3
5
4
OÇ-3
3
3
5
5
5
3
4
5
5
5
4
OÇ-4
3
3
3
3
4
3
4
3
3
4
4
OÇ-5
4
4
4
3
5
4
3
4
4
4
4
Adnan Menderes University - Information Package / Course Catalogue
2026