Virtually all NLP systems nowadays use vector representations of words, a.k.a. word embeddings. Similarly, the processing of language combined with vision or other sensory modalities employs multimoda
A remaining major challenge with autonomous systems is the handling of situations that the system cannot handle on its own. Up to now, this transfer of control has been considered in isolation. An imp
Das Forschungsvorhaben beschäftigt sich mit der wahrgenommenen Qualität von maschinell generierten Texten. Der Fokus liegt hierbei auf den beiden Texttypen maschinelle Übersetzung und maschinelle Zusa
The SPEAKER project seeks to develop a leading German-made voice assistant platform for business-to-business (B2B) applications. This platform should be open, modular and scalable and provide technolo
The ability to read and to understand text is a crucial competence to communicate and to exchange information. For different reasons, understanding written language can be a challenge for different ta
Until today, audio or media guides accompany exhibition visits and offer explanations for museum objects. The CHIM project aims to develop a learning, conversational museum guide that enables interact
The project aims to create a personal virtual assistant that provides psychological and social support to migrants and public services. The intelligent service will act as a multilingual agent in the
Language is an essential part of our lives – we use it to share information, to describe our feelings, to discuss with others or to pass on knowledge to the next generations. It is a vital component o
The project objective is to take advantage of the advances in Big Data, Artificial Intelligence and Machine Learning to support cancer patients’ quality of life and health status. To this end, it will
AI is on everyone’s lips. Applications of AI are becoming increasingly relevant in the field of clinical decision-making. While many of the conceivable use cases of clinical AI still lay in the future