Supervision & Teaching
Supervision
Teaching
Current Teaching offers
Please have a look at our current selection of courses, labs and seminars if you are interested to join those.
Seminar Knowledge Graph Representation Learning at TU Dresden
Representation learning is a set of methods which allows finding suitable feature representations of input data to perform particular tasks. Such methods can be applied on textual data (e.g. via language models), images and structured data. The resulting features are usually called embeddings. In this seminar, we study representation learning methods for knowledge graphs.
The seminar will cover recent state-of-the-art research in knowledge graph representation learning (KGRL) such as:
- Preservation of relational and structural patterns of KGRL approaches
- Scalability to large knowledge graphs
- Inductive reasoning approaches
- KGRL for hyper-relational graphs
- Temporal knowledge graph support
- Multi-modal KGRL approaches
- Combinations of language models and KGRL
- Distillation methods
- Impact of different geometric spaces
- Bias in knowledge graph embeddings
- Support for rules & ontologies in KGRL approaches
Registration: To participate in the seminar, please register via Selma. You can find the list of topics in the slides of the seminar. If you want to select one of the topics, please contact me via mail.
Seminar Conversational AI at TU Dresden
This seminar provides an extensive exploration into the realm of Conversational AI, covering both technical and scientific perspectives as well as some ethical considerations. It delves into the intricate process of training models to understand and interpret human languages, answer questions, and make decisions based on a variety of data inputs. The seminar sessions examine the emerging capabilities and challenges in building general AI approaches, including different sources of information, emergent abilities of AI systems, reasoning techniques and responsible AI.
(image by Midjourney)
Registration: To participate in the seminar, please register via Selma and OPAL. You can find the list of topics in the slides of the seminar.