VBM682 - NATURAL LANGUAGE PROCESSING
| Course Name | Code | Semester | Theory (hours/week) |
Application (hours/week) |
Credit | ECTS |
|---|---|---|---|---|---|---|
| NATURAL LANGUAGE PROCESSING | VBM682 | Any Semester/Year | 3 | 0 | 3 | 6 |
| Prequisites | - | |||||
| Course language | Turkish | |||||
| Course type | Elective | |||||
| Mode of Delivery | Face-to-Face | |||||
| Learning and teaching strategies | Lecture Preparing and/or Presenting Reports Problem Solving Project Design/Management | |||||
| Instructor (s) | Prof. Dr. İlyas Çiçekli | |||||
| Course objective | The objective of this course is to teach main paradigms and algorithms in natural language processing. Capabilities and application areas of machine learning algrorithms are taught. | |||||
| Learning outcomes |
| |||||
| Course Content | ? Learn how to do research, how to implement a project and how to write a scientific paper in natural language processing area. | |||||
| References | 1. Daniel Jurafsky, and James H. Martin, "Speech and Language Processing", Prentice Hall, 2000. 2. James Allen, "Natural Language Understanding", Second edition, The Benjamin/Cumings Publishing Company Inc., 1995. 3. Christopher D. Manning, and Hinrich Schutze, "Foundations of Statistical Natural Language Processing", The MIT Press, 1999. 1. Pierre M. Nugues, ?An Introduction to Language Processing with Perl and Prolog?, Springer, 2006. | |||||
Course outline weekly
| Weeks | Topics |
|---|---|
| Week 1 | Overview of Natural Language Processing |
| Week 2 | Morphological Processing |
| Week 3 | Morphological Processing |
| Week 4 | Stattictical Methods |
| Week 5 | Part-of-Speech Tagging |
| Week 6 | Parsing for Context-Free-Languages |
| Week 7 | Parsing Methods for Natutural Languages ? Earley, CYK Parsing Methods |
| Week 8 | Lexicalized and Probabilistic Parsing |
| Week 9 | Semantic Analysis |
| Week 10 | Semantic Analysis |
| Week 11 | Discourse |
| Week 12 | Applications of Natural Language Processing ? Machine Translation |
| Week 13 | Applications of Natural Language Processing ? Information Extraction, Text Summarization |
| Week 14 | Project presentations |
| Week 15 | |
| Week 16 | Final exam |
Assesment methods
| Course activities | Number | Percentage |
|---|---|---|
| Attendance | 0 | 0 |
| Laboratory | 0 | 0 |
| Application | 0 | 0 |
| Field activities | 0 | 0 |
| Specific practical training | 0 | 0 |
| Assignments | 0 | 0 |
| Presentation | 0 | 0 |
| Project | 1 | 50 |
| Seminar | 0 | 0 |
| Midterms | 0 | 0 |
| Final exam | 1 | 50 |
| Total | 100 | |
| Percentage of semester activities contributing grade succes | 1 | 50 |
| Percentage of final exam contributing grade succes | 1 | 50 |
| Total | 100 | |
WORKLOAD AND ECTS CALCULATION
| Activities | Number | Duration (hour) | Total Work Load |
|---|---|---|---|
| Course Duration (x14) | 14 | 3 | 42 |
| Laboratory | 0 | 0 | 0 |
| Application | 0 | 0 | 0 |
| Specific practical training | 0 | 0 | 0 |
| Field activities | 0 | 0 | 0 |
| Study Hours Out of Class (Preliminary work, reinforcement, ect) | 14 | 3 | 42 |
| Presentation / Seminar Preparation | 0 | 0 | 0 |
| Project | 1 | 60 | 60 |
| Homework assignment | 0 | 0 | 0 |
| Midterms (Study duration) | 0 | 0 | 0 |
| Final Exam (Study duration) | 1 | 25 | 25 |
| Total Workload | 30 | 91 | 169 |
Matrix Of The Course Learning Outcomes Versus Program Outcomes
| D.9. Key Learning Outcomes | Contrubition level* | ||||
|---|---|---|---|---|---|
| 1 | 2 | 3 | 4 | 5 | |
| 1. Has detailed knowledge about data and knowledge engineering (DKE). | X | ||||
| 2. Has a good understanding of common concepts such as abstraction, complexity, security, concurrency, software lifecycle and applies their expertise to the effective design, development and management of IS. | X | ||||
| 3. Understands the interaction of theory and practice and the links between them. | X | ||||
| 4. Has the ability to think at different levels of abstraction and detail; understands that an IS can be considered in different contexts, going beyond narrowly identifying implementation issues. | X | ||||
| 5. Solves any technical or scientific problem independently and presents the best possible solution; has the communication skills to clearly explain the completeness and assumptions of their solution. | X | ||||
| 6. Completes a project on a larger scale than an ordinary course project in order to acquire the skills necessary to work efficiently in a team. | X | ||||
| 7. Recognises that the field of DKE is rapidly evolving. Follows the latest developments, learns and develops skills throughout their career. | X | ||||
| 8. Recognises the social, legal, ethical and cultural issues related to DKE practice and conduct professional activities in accordance with these issues. | X | ||||
| 9. Can make oral presentations in English and Turkish to different audiences face-to-face, in writing or electronically. | X | ||||
| 10. Recognises that DKE has a wide range of applications and opportunities. | X | ||||
| 11. Is aware that DKE interacts with different fields, can communicate with experts from different fields and can learn necessary field knowledge from them. | X | ||||
| 12. Define a research problem and use scientific methods to solve it. | X | ||||
*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest