Natural Language Processing(MAT410)
| Course Code | Course Name | Semester | Theory | Practice | Lab | Credit | ECTS |
|---|---|---|---|---|---|---|---|
| MAT410 | Natural Language Processing | 8 | 3 | 0 | 0 | 3 | 5 |
| Prerequisites | |
| Admission Requirements |
| Language of Instruction | English |
| Course Type | Elective |
| Course Level | Bachelor Degree |
| Course Instructor(s) | Muhammed ULUDAĞ muhammed.uludag@gmail.com (Email) |
| Assistant | |
| Objective | The course aims to provide an in-depth understanding of Natural Language Processing (NLP), exploring both foundational concepts and advanced techniques. It is designed to equip students with the theoretical knowledge and practical skills necessary to apply NLP in real-world applications, such as text classification, sentiment analysis, machine translation, and question-answering systems. |
| Content |
ntroduction to NLP: Overview of NLP and its applications. Text Processing: Basic text preprocessing, tokenization, stemming, lemmatization. Language Models: N-grams, probabilistic models, neural network-based models. Part-of-Speech Tagging and Named Entity Recognition: Techniques and applications. Syntax and Parsing: Sentence structure analysis, dependency parsing. Semantics: Word embeddings, contextual embeddings (BERT, GPT). Machine Translation: Approaches to automatic translation, sequence-to-sequence models. Question Answering and Chatbots: Building systems that understand and generate human-like responses. Ethical Considerations in NLP: Bias, fairness, and implications of NLP technologies. |
| Course Learning Outcomes |
By the end of the course, students will be able to: Understand and explain the fundamental principles of NLP. Implement NLP tasks using Python and relevant libraries (e.g., NLTK, spaCy, TensorFlow, PyTorch). Apply machine learning and deep learning models to solve NLP problems. Critically evaluate NLP models, considering their performance, limitations, and ethical implications. Design and develop their own NLP applications for real-world problems. |
| Teaching and Learning Methods |
The course will employ a blend of teaching methods to foster a comprehensive learning experience: Lectures: To introduce concepts and theories, using Chris Manning's online lectures supplemented with additional materials. Hands-on Labs: Practical sessions where students apply concepts using NLP tools and libraries. Case Studies: Analysis of real-world NLP applications and research papers. Group Projects: Encourage collaboration on larger NLP projects. Quizzes and Assignments: To reinforce learning and assess progress. |
| References |
1- Speech and Language Processing, D. Jurafsky& J.H. Martin, https://web.stanford.edu/~jurafsky/slp3/ 3rd edition draft 2- Foundation of Statistical Natural Language Processing, C.D. Manning & H. Schütze, MIT Press, 2003 3- Natural Language Processing with Python, Steven Bird, Ewan Klein, and Edward Loper O’Reilly, 2009: http://www.nltk.org/book/ Supplementary Books: 4- Python 3 Text Processing with NLTK 3 Cookbook, Jacob Perkins, Packt Publishing, 2014 5- Applied Text Analysis with Python, Benjamin Bengfort, Tony Ojeda, Rebecca Bilbro, O’Reilly, 2018 6- Turkish Natural Language Processing, Kemal Oflazer, Murat Saraçlar, Springer, 2018 7- Neural Network Methods for Natural Language Processing, Yoav Goldberg, Morgan & Claypool, 2017 |
Theory Topics
| Week | Weekly Contents |
|---|---|
| 1 | Introduction to NLP; history and applications. |
| 2 | Text processing basics; working with text data. |
| 3 | Language models; introduction to n-grams and probabilistic models |
| 4 | Advanced language models; introduction to neural networks in NLP. |
| 5 | Part-of-Speech tagging; understanding and implementing tagging algorithms. |
| 6 | Named Entity Recognition; techniques and tools. |
| 7 | Syntax and Parsing; analyzing sentence structure. |
| 8 | Semantics; exploring word embeddings and contextual embeddings. |
| 9 | Machine Translation; understanding and building translation models. |
| 10 | Advanced topics in machine translation; exploring state-of-the-art models. |
| 11 | Question Answering and Chatbots; designing systems for interaction. |
| 12 | Ethical considerations in NLP; discussing bias, fairness, and social impact. |
| 13 | Group project presentations; applying what has been learned. |
| 14 | Course wrap-up; review and final exams. |
Practice Topics
| Week | Weekly Contents |
|---|
Contribution to Overall Grade
| Number | Contribution | |
|---|---|---|
| Contribution of in-term studies to overall grade | 1 | 40 |
| Contribution of final exam to overall grade | 1 | 60 |
| Toplam | 2 | 100 |
In-Term Studies
| Number | Contribution | |
|---|---|---|
| Assignments | 2 | 25 |
| Presentation | 0 | 0 |
| Midterm Examinations (including preparation) | 0 | 0 |
| Project | 1 | 25 |
| Laboratory | 0 | 0 |
| Other Applications | 0 | 0 |
| Quiz | 0 | 0 |
| Term Paper/ Project | 0 | 0 |
| Portfolio Study | 0 | 0 |
| Reports | 0 | 0 |
| Learning Diary | 0 | 0 |
| Thesis/ Project | 0 | 0 |
| Seminar | 0 | 0 |
| Other | 0 | 0 |
| Toplam | 3 | 50 |
| No | Program Learning Outcomes | Contribution | ||||
|---|---|---|---|---|---|---|
| 1 | 2 | 3 | 4 | 5 | ||
| 1 | understands principles of deductive reasoning; has experience to verify well-foundedness and exactness of mathematical statements in systematic ways; | |||||
| 2 | can properly state and use concepts and results of major mathematical interest; | X | ||||
| 3 | masters current computational techniques and algorithms; has a good ability in their use; can identify relevant tools, among those one has learned, suitable to solve a problem and is able to judge whether or not one is in possession of these tools; | X | ||||
| 4 | is able to express one’s mathematical ideas in an organised way both in written and oral forms; | X | ||||
| 5 | understands relations connecting substantial concepts and results; can switch from one viewpoint to another on mathematical objects (pictures, formulae, precise statements, heuristic trials, list of examples,...); | X | ||||
| 6 | has followed individually a guided learning strategy; has pursued steps toward the resolution of unfamiliar problems; | X | ||||
| 7 | has a theoretical and practical knowledge in computer science well adapted for learning a programming language; | X | ||||
| 8 | has investigated the relevance of modeling and using mathematical tools in natural sciences and in the professional life; is conscious about historical development of mathematical notions; | X | ||||
| 9 | has followed introduction to some mathematical or non-mathematical disciplines after one’s proper choice; had experience to learn selected subjects according to one’s proper arrangement; | X | ||||
| 10 | masters French language as well as other foreign languages, to a level sufficient to study or work abroad. | X | ||||
| Activities | Number | Period | Total Workload |
|---|---|---|---|
| Class Hours | 14 | 3 | 42 |
| Working Hours out of Class | 14 | 1 | 14 |
| Assignments | 4 | 15 | 60 |
| Presentation | 0 | 0 | 0 |
| Midterm Examinations (including preparation) | 1 | 7 | 7 |
| Project | 0 | 0 | 0 |
| Laboratory | 0 | 0 | 0 |
| Other Applications | 0 | 0 | 0 |
| Final Examinations (including preparation) | 1 | 10 | 10 |
| Quiz | 0 | 0 | 0 |
| Term Paper/ Project | 1 | 4 | 4 |
| Portfolio Study | 0 | 0 | 0 |
| Reports | 0 | 0 | 0 |
| Learning Diary | 0 | 0 | 0 |
| Thesis/ Project | 0 | 0 | 0 |
| Seminar | 0 | 0 | 0 |
| Other | 0 | 0 | 0 |
| Total Workload | 137 | ||
| Total Workload / 25 | 5,48 | ||
| Credits ECTS | 5 | ||