Our research on conversational AI and knowledge extraction brings together knowledge graphs, natural language understanding, and deep learning. Goals include:

1. Fast domain adaptation techniques in goal-driven dialogs for context-sensitive, coherent, and correct responses.
2. Code synthesis for data analytics, with focus on foundational paradigm shifts (e.g., transformer-based encoding of tree structures).
3. Conversational search for exploring research, e.g., recent COVID-19 related research; building on our expertise in question answering.
4. Explainability approaches based on graph representations.

Team

Lead

• Prof. Dr. Martin Potthast