A human can read a book and instantly be able to talk about what he or she has read. Machines, on the other hand, are very good in storing huge amount of information but not so good in sharing this information with humans in a natural and human-like way. The question we try to answer is how we enrich dialogue system knowledge using non-dialogue unstructured data and what is the adequate dialogue system architecture and features which are needed to support that.

• Duration: 01.12.2018 - 31.10.2024
• Value: 1.65M Euro
• People: Prof. Dr Milica Gasic, Dr Michael Heck, Dr Nurul Lubis, Carel van Niekerk and Shutong Feng

The dialogue systems currently deployed both in academia and in industry are typically built for fixed domains, requiring a new data set every time the domain changes.  End-to-end methods attempting to solve this problem directly with open-domain chat-bots are far from reaching competitive results on goal-oriented tasks.  The aim of this project is to tackle the most substantial obstacles on the way to intelligent conversational systems that can expand dynamically and span the problem of operating with dynamic knowledge, dynamic policies, rich user models and sophisticated measures of quality.

• Duration: 01.09.2019 - 31.01.2026
• Value: 1.5M Euro
• People: Prof. Dr Milica Gasic, Christian Geishauser, Hsien-Chin Lin, Benjamin Ruppik and Renato Vukovic

Large language models achieve impressive results across the entire spectrum of computational linguistics. Their success is based on an innovative combination of three mechanisms: a transformer network, prompt-based learning and reinforcement learning through human feedback. As impressive as the capabilities of these language models are, the problems they bring with them are just as diverse.

Large language models need to be trained on huge data sets. Accessing the models is costly and time-consuming. The output includes misleading content with no apparent reference to the training data. There is no evidence of the reliability. The models lack the ability to seamlessly incorporate external knowledge into their outputs.

Large language models are therefore not a replacement for conventional human-computer interfaces. However, they have the potential to take the quality and user-friendliness of such interfaces to a whole new level. The central question that we would like to address as part of this project is: How and where is it necessary and responsible to integrate large language models into an interactive human-computer dialogue system? The project therefore lies at the intersection of human-focused artificial intelligence, trustworthy artificial intelligence and linguistic data processing.

• Duration: 01.04.2024 – 31.03.2028
• Value: 599.222,14 Euro
• People: Prof. Dr. Milica Gasic, Dr. Carel van Niekerk und Dr. Hsien-Chin Lin