Advanced Natural Language ProcessingModule description #41270 / Version 1
- 6 CP
- Portfolio examination
- Graded
- Winter semester
- English
| Module / Version | #41270 / #1 |
|---|---|
| Validity | Since Winter semester 2025/26 |
| Available language(s) | English, German |
| Credit points | 6 |
| Person responsible for the module | Möller, Sebastian |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34355300 FG S-Professur Quality and Usability |
Contact
| Office | MAR 6-7 |
|---|---|
| Contact person | Jettkowski, Tobias |
| E-mail address | module@qu.tu-berlin.de |
| Website | https://www.tu.berlin/qu/studium-und-lehre/lehrangebot |
Learning outcomes
Upon successful completion of this module, students will be able to:
- Describe and analyze key concepts of large language models (LLMs), including language modeling, attention mechanisms, transformer architectures, pre-training, fine-tuning, and instruction tuning;
- Explain advanced techniques such as reinforcement learning with human feedback (RLHF) and retrieval-augmented generation (RAG), and assess their areas of application;
- Apply LLMs to typical natural language processing (NLP) tasks such as text generation, summarization, machine translation, and conversational systems, and evaluate their suitability for specific tasks;
- Develop domain-specific applications, e.g. in the healthcare sector, while considering issues such as data privacy, fairness, and misinformation detection.
- Describe and analyze key concepts of large language models (LLMs), including language modeling, attention mechanisms, transformer architectures, pre-training, fine-tuning, and instruction tuning;
- Explain advanced techniques such as reinforcement learning with human feedback (RLHF) and retrieval-augmented generation (RAG), and assess their areas of application;
- Apply LLMs to typical natural language processing (NLP) tasks such as text generation, summarization, machine translation, and conversational systems, and evaluate their suitability for specific tasks;
- Develop domain-specific applications, e.g. in the healthcare sector, while considering issues such as data privacy, fairness, and misinformation detection.
Content
This course presents current foundational topics in natural language processing with a focus on large language models (LLMs). The content includes key concepts such as sequence modeling, attention mechanisms, transformers, pre-training and fine-tuning of LLMs, prompting, reinforcement learning from human feedback (RLHF), and retrieval-augmented generation (RAG). Additionally, various NLP tasks such as text generation, summarization, machine translation, conversational AI, information extraction, and domain-specific applications (e.g., in healthcare) are discussed. Important ethical and technical issues, including privacy, fairness, text anonymization, and misinformation detection, are also covered.
The course includes hands-on project work where students apply the learned techniques to real-world problems. Therefore, basic knowledge of Python programming, machine learning, and natural language processing is recommended.
The course includes hands-on project work where students apply the learned techniques to real-world problems. Therefore, basic knowledge of Python programming, machine learning, and natural language processing is recommended.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Advanced Natural Language Processing | Integrated course | Winter semester | [en] | 3 | WS 2026/27 (2) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Advanced Natural Language Processing (Integrated course) 2
Workload and credit points
Advanced Natural Language Processing (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 12 | 3 h | 36 h |
| Project | 3 | 20 h | 60 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 156 h | |||
The workload of the module adds up to 156 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Studying the online video content on the learning platform, participating in discussions and asking questions on the forum, and completing quizzes and projects.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Basic knowledge of Python programming, natural language processing, and machine learning is recommended.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| (Examination) Written test | 40 | written | 60 minutes |
| (Deliverable assessment) Project results | 60 | practical | Ap. 20 Pages |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
The maximum capacity of participants is 50.
Registration procedures
Contact the course supervisor
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
No recommended literature given
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
| SS 2026 | Wahlpflicht Studiengebiet B › Medientechnik und Mensch-Maschine-Interaktion / Digital Media und Human-Computer Interaction | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet A › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
| SS 2026 | Studiengebiete › Medientechnik und Mensch-Maschine-Interaktion / Digital Media und Human-Computer Interaction | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Medientechnik und Mensch-Maschine-Interaktion / Digital Media und Human-Computer Interaction | |
| Digital Media and Technology Digital Media and Technology (M. Sc.) - StuPO 2017 | WS 2025/26 | Wahlpflichtbereich › Technische Profilbereiche (A) › Profilbereich Mensch-Maschine-Interaktion |
| SS 2026 | Wahlpflichtbereich › Technische Profilbereiche (A) › Profilbereich Mensch-Maschine-Interaktion | |
| WS 2026/27 | Wahlpflichtbereich › Technische Profilbereiche (A) › Mensch-Maschine-Interaktion | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
| SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction | |
| Media Technology Media Technology (M. Sc.) - StuPO 2022 | WS 2025/26 | Wahlpflicht weitere Profibereiche › weiterer Profilbereich Mensch-Maschine-Interaktion |
| SS 2026 | Wahlpflichtbereich Profilbereiche › Profilbereich Mensch-Maschine-Interaktion | |
| WS 2026/27 | Wahlpflichtbereich › Profilbereich › Mensch-Maschine-Interaktion |
Miscellaneous
Not specified