INFORMATION TECHNOLOGIES (MASTER) (WITH THESIS) (ENGLISH)
Qualification Awarded	Program Süresi	Toplam Kredi (AKTS)	Öğretim Şekli	Yeterliliğin Düzeyi ve Öğrenme Alanı
Master's ( Second Cycle) Degree	2	120	FULL TIME	TYÇ, TR-NQF-HE, EQF-LLL, ISCED (2011):Level 7 QF-EHEA:Second Cycle TR-NQF-HE, ISCED (1997-2013): 44,46,48,52,72

Ders Genel Tanıtım Bilgileri

Course Code:

3000004006

Ders İsmi:

Natural Language Processing

Ders Yarıyılı:

Fall

Ders Kredileri:

Theoretical	Practical	Labs	Credit	ECTS
3	0	0	3	6

Language of instruction:

Ders Koşulu:

Ders İş Deneyimini Gerektiriyor mu?:

Other Recommended Topics for the Course:

Type of course:

Department Elective

Course Level:

Master

TR-NQF-HE:7. Master`s Degree

QF-EHEA:Second Cycle

EQF-LLL:7. Master`s Degree

Mode of Delivery:

Face to face

Course Coordinator :

Dr.Öğr.Üyesi Recep DURANAY

Course Lecturer(s):

Course Assistants:

Dersin Amaç ve İçeriği

Course Objectives:

Yapay zekanın bir alt dalı olan Doğal Dil İşleme, insanların kullandığı dili işlemek için teknikler geliştirmeyi amaçlar. Bu teknikler kullanılarak insan-makine iletişiminin arttırılması, makine çevirisi, hızlı bilgi çıkarımı gibi birçok konuda uygulamalar geliştirilmektedir. Bu dersin amacı, Doğal Dil İşlemedeki temel teknikleri ve bu konudaki güncel araştırmaların bir kısmını tanıtmaktır.

Course Content:

The course "Natural Language Processing (NLP) - Mastering Text Understanding" is a comprehensive and practical exploration of the fascinating world of NLP, designed for students at the Master's degree level. NLP is a dynamic field that empowers computers to comprehend and process human language, enabling applications such as sentiment analysis, machine translation, and chatbots. Throughout this 14-week semester, students will dive into the core concepts and methodologies of NLP, equipping them with the knowledge and skills to tackle complex text-based challenges. Starting with an introduction to NLP and text preprocessing, students will explore text representation techniques like word embeddings and language modeling. They will delve into tasks such as part-of-speech tagging, sentiment analysis, and text classification using both traditional machine learning algorithms and deep learning approaches. With hands-on coding and projects, students will become proficient in text summarization, machine translation, named entity recognition, and question answering. They will understand the essentials of dependency parsing, constituency parsing, and named entity linking, gaining practical experience in building NLP systems. The course also delves into advanced NLP topics, such as topic modeling, NLP for social media, and ethical considerations surrounding NLP applications. By the end of the course, students will emerge as skilled NLP practitioners, capable of processing and analyzing text data, and making informed decisions in leveraging the power of NLP for various real-world applications. Whether aspiring to develop language understanding models or use NLP in business intelligence, this course prepares students to be at the forefront of the NLP revolution.

Learning Outcomes

The students who have succeeded in this course;

Learning Outcomes

1 - Knowledge
Theoretical - Conceptual
1) Comprehensive Understanding of NLP Fundamentals: Students will acquire a deep understanding of the fundamental concepts and techniques used in Natural Language Processing. They will be able to explain the challenges in processing human language, the importance of tokenization, and various text preprocessing techniques.
2) 3. Application of Deep Learning for NLP: Students will explore deep learning approaches in NLP, including recurrent neural networks (RNNs) for text generation and convolutional neural networks (CNNs) for text classification. They will learn how to build sequence-to-sequence models for machine translation and apply attention mechanisms in NLP tasks.
3) 4. Ethical Considerations in NLP: Students will examine the ethical implications of NLP applications, including privacy concerns, bias in language models, and social impact. They will be equipped to critically assess the ethical dimensions of NLP projects and make responsible decisions in their applications.
4) Research and Innovation in NLP: Students will be exposed to cutting-edge research and emerging trends in NLP. They will have the opportunity to explore advanced topics such as topic modeling, NLP for social media, and the latest developments in machine comprehension models for question answering.
2 - Skills
Cognitive - Practical
3 - Competences
Communication and Social Competence
Learning Competence
1) Practical Proficiency in NLP Techniques: Students will gain hands-on experience in implementing key NLP techniques, such as sentiment analysis, named entity recognition, and text summarization. They will develop the ability to apply text representation methods like word embeddings and language modeling to solve real-world text understanding tasks.
Field Specific Competence
Competence to Work Independently and Take Responsibility

Ders Akış Planı

Week	Subject	Related Preparation
1)	Introduction to Natural Language Processing - Overview of NLP and its applications - Challenges in NLP: Ambiguity, context, and syntax - Tokenization and text preprocessing	textbook
2)	Text Representation and Feature Engineering - Bag-of-Words model and TF-IDF - Word embeddings (Word2Vec, GloVe) - Pre-trained language models (BERT, GPT)	textbook
3)	Language Modeling and Text Generation - N-gram language models - Recurrent Neural Networks (RNNs) for text generation - Sequence-to-Sequence models and attention mechanisms
3)	Natural Language Processing Basics 1. Introduction to NLP Processing 2. Spacy Basics 3. Tokenization 4. Stemming 5. Lemmatization 6. Stop Words 7. Phrase Matching and Vocabulary	textbook
4)	Part of Speech Tagging and Named Entity Recognition 1. Introduction to Part of Speech (POS) 2. POS Tagging 3. Visualizing POS 4. Named Entity Recognition and Visualization 5. Sentence Segmentation	textbook
4)	Part-of-Speech Tagging and Named Entity Recognition - POS tagging algorithms - Named Entity Recognition (NER) techniques
5)	Sentiment Analysis - Sentiment analysis approaches: Rule-based, ML, and deep learning - Handling sentiment in different languages	textbook
6)	Text Classification - Naive Bayes Classifier - Support Vector Machines (SVM) for text classification - Text classification with deep learning (CNN, LSTM)	textbook
7)	Text Summarization - Extractive summarization techniques - Abstractive summarization using seq2seq models	textbook
8)	midterm exam	textbook
9)	ext Translation - Machine Translation fundamentals - Neural Machine Translation (NMT) using attention	textbook
10)	Named Entity Linking and Coreference Resolution - Named Entity Linking (NEL) approaches - Coreference resolution algorithms	textbook
11)	Dependency Parsing and Constituency Parsing - Dependency parsing methods - Constituency parsing techniques	textbook
12)	Information Retrieval and Question Answering - TF-IDF for information retrieval - Question Answering with machine comprehension models	textbook
13)	Advanced NLP Topics - Topic modeling (LDA) - NLP for social media and web text - Ethical considerations in NLP	textbook
14)	Final	textbook

Sources

Course Notes / Textbooks:	Python Natural Language Processing , Jalaj Thanaki Edition 1
References:	Python Natural Language Processing , Jalaj Thanaki Edition 1

Ders - Program Öğrenme Kazanım İlişkisi

Ders Öğrenme Kazanımları	1	3	4	5	2
Program Outcomes
1) Ability to use and apply current technical concepts and practices in the information technologies of engineering, data management and computer security.
2) Understanding user needs, analyzing them, and using them in the selection, evaluation, and management of computer-based systems.
3) Ability to use data structures and develop algorithms.
4) Ability to analyze and interpret complex big data systems.
5) Ability to interpret and apply concepts and algorithms in machine learning.
6) Understanding of the mathematical foundations of deep learning in the field of data analysis and the ability to apply the theory.
7) Ability to solve complex data structures, develop and apply deep learning models, and interpret artificial intelligence-focused research on these topics.
8) Ability to apply deep learning techniques and interpret real-world datasets and projects to solve problems in image analysis, natural language processing, and recommendation systems.
9) Ability to transfer the basic principles and mathematical infrastructure of digital signal processing to practical applications.
10) Gaining knowledge about the tools and technologies used via the Internet and the different technologies used for server coding languages and tools.
11) Ability to understand of how genes function in multicellular species, the flow of genetic information in single-cell organisms, and the ability to interpret and apply biotechnology applications.
12) Being aware of ethical values and understanding the need to conduct research and practice within the framework of these values.

Ders - Öğrenme Kazanımı İlişkisi

No Effect	1 Lowest	2 Low	3 Average	4 High	5 Highest

	Program Outcomes	Level of Contribution
1)	Ability to use and apply current technical concepts and practices in the information technologies of engineering, data management and computer security.
2)	Understanding user needs, analyzing them, and using them in the selection, evaluation, and management of computer-based systems.
3)	Ability to use data structures and develop algorithms.
4)	Ability to analyze and interpret complex big data systems.
5)	Ability to interpret and apply concepts and algorithms in machine learning.
6)	Understanding of the mathematical foundations of deep learning in the field of data analysis and the ability to apply the theory.
7)	Ability to solve complex data structures, develop and apply deep learning models, and interpret artificial intelligence-focused research on these topics.
8)	Ability to apply deep learning techniques and interpret real-world datasets and projects to solve problems in image analysis, natural language processing, and recommendation systems.
9)	Ability to transfer the basic principles and mathematical infrastructure of digital signal processing to practical applications.
10)	Gaining knowledge about the tools and technologies used via the Internet and the different technologies used for server coding languages and tools.
11)	Ability to understand of how genes function in multicellular species, the flow of genetic information in single-cell organisms, and the ability to interpret and apply biotechnology applications.
12)	Being aware of ethical values and understanding the need to conduct research and practice within the framework of these values.

Öğrenme Etkinliği ve Öğretme Yöntemleri

Bireysel çalışma ve ödevi
Grup çalışması ve ödevi
Web Tabanlı Öğrenme

Ölçme ve Değerlendirme Yöntemleri ve Kriterleri

Yazılı Sınav (Açık uçlu sorular, çoktan seçmeli, doğru yanlış, eşleştirme, boşluk doldurma, sıralama)
Homework
Uygulama

Assessment & Grading

Semester Requirements	Number of Activities	Level of Contribution
Homework Assignments	1	% 20
Midterms	1	% 40
Semester Final Exam	1	% 40
total		% 100
PERCENTAGE OF SEMESTER WORK		% 60
PERCENTAGE OF FINAL WORK		% 40
total		% 100

İş Yükü ve AKTS Kredisi Hesaplaması

Activities	Number of Activities	Duration (Hours)	Workload
Course Hours	3	14	42
Study Hours Out of Class	14	6	84
Homework Assignments	2	20	40
Midterms	1	2	2
Final	1	3	3
Total Workload			171