Courses and Seminars
Current Teaching
| Course | Home institute | Lecturer | Semester | Type | Language |
|---|
Course Offerings and Content
Ever wondered how Large Language Models work in detail? Natural Language Processing (NLP) is an interdisciplinary field that combines linguistics, computer science, and artificial intelligence to enable computers to understand and generate human language. Recent progress in NLP has been fueled by large datasets and powerful deep learning models.
By the end of this course, you will be able to recognize different types of NLP problems and select appropriate state‑of‑the‑art methods to solve them. You will also learn to critically assess the strengths, limitations, and ethical implications of NLP solutions. Throughout the course, you will further develop your logical, analytical, and conceptual thinking skills and gain experience in scientific reasoning.
In our practical exercises, we will use state-of-the-art machine learning toolkits – prior knowledge of Python (ideally having participated in INF-0487) is highly recommended!
Note: This course is also available as a prepatory course (INF-8805 Preparatory Course Python Programming) for Master students with an interdisciplinary background that would like to brush up or deepen their programming skills.
The Python programming language is of great importance in today's technology landscape due to its versatility and ease of use. It serves as a powerful language for tasks ranging from web development and data analysis to artificial intelligence and automation, making it an indispensable tool for both beginners and experienced developers in numerous industries and research fields.
This module conveys fundamental concepts of computer science with a focus on data structures, algorithms, and their implementation in the Python programming language. Students learn to analyze algorithmic problems, select appropriate data structures, and design and implement efficient solution approaches.
Topics covered include basic and composite data structures (e.g., lists, stacks, queues, dictionaries, sets) as well as fundamental algorithms (e.g., searching, sorting, recursion). In addition, principles of good software development are introduced, including modular programming, clear and readable code structures, simple testing methods, and the fundamentals of object-oriented programming.
Through practice-oriented programming assignments, students acquire basic skills in working with Python and develop solid algorithmic thinking, which forms an important foundation for further courses in computer science, data analysis, and machine learning. As part of the course, basic knowledge of several widely used Python frameworks is also taught.
This seminar introduces students to Natural Language Understanding (NLU), the field of artificial intelligence focused on enabling computers to understand, interpret, and generate human language. The seminar explores how modern approaches such as machine learning, deep learning, generative AI, and large language models (LLMs) are transforming natural language processing.
Students will learn the fundamental concepts behind language representation, neural networks, and transformer-based models, and how these techniques are applied in real-world systems such as chatbots, virtual assistants, search engines, and text analysis tools. The seminar also highlights current research trends, practical challenges, and ethical considerations related to large-scale language models.
Through paper discussions, hands-on exercises, and student presentations, participants will gain both theoretical understanding and practical insight into how state-of-the-art NLU systems are built and evaluated.
Topics may include:
* Basics of Natural Language Processing and Understanding
* Machine learning and deep learning for text data
* Transformer architectures and large language models
* Generative AI for text generation and dialogue systems
* Evaluation methods and limitations of language models
* Ethical, societal, and environmental implications of generative AI----
Neural Information Retrieval leverages the power of neural networks to enhance the representation, understanding, and retrieval of information, addressing many of the challenges posed by the complexity and variability of natural language. With the recent development in the area of large language models (or more generally, foundation models), novel approaches to interactive information retrieval are developing.
After taking part in the course, students are able to explain the concepts and methods, procedures, techniques and technologies related to neural information retrieval. In particular, the course covers:
-
Basics of traditional information retrieval methods
-
Vector-based document and query representations (topic modeling and neural representations)
-
Ranking with embeddings
-
Question answering, entity search, and knowledge graphs
-
Multimodal retrieval
-
Interactive information retrieval and personalization
Students will be able to recognise important technical developments in the field of information retrieval. They can apply machine learning procedures, such as feature extraction, embedding learning, and pattern recognition, to information retrieval problems. They will be able to perform literature research in the area of information retrieval, and identify gaps in the state-of-the-art. They know how to make scientifically meaningful evaluations of proposed systems. They will further learn how to document and present results and complex ideas in a reasonable and meaningful way. Participants will also deepen their programming skills in Python.
This seminar introduces students to Natural Language Understanding (NLU), the field of artificial intelligence focused on enabling computers to understand, interpret, and generate human language. The seminar explores how modern approaches such as machine learning, deep learning, generative AI, and large language models (LLMs) are transforming natural language processing.
Students will learn the fundamental concepts behind language representation, neural networks, and transformer-based models, and how these techniques are applied in real-world systems such as chatbots, virtual assistants, search engines, and text analysis tools. The seminar also highlights current research trends, practical challenges, and ethical considerations related to large-scale language models.
Through paper discussions, hands-on exercises, and student presentations, participants will gain both theoretical understanding and practical insight into how state-of-the-art NLU systems are built and evaluated.
Topics may include:
* Basics of Natural Language Processing and Understanding
* Machine learning and deep learning for text data
* Transformer architectures and large language models
* Generative AI for text generation and dialogue systems
* Evaluation methods and limitations of language models
* Ethical, societal, and environmental implications of generative AI----