Almost every day we interact with chatbots, which now provide a user-friendly interface to information sources and various services. Whether it's questions about insurance benefits, the processing status of a loan or parcel tracking, most of these interactions are question and answer scenarios that can be implemented within a given context using Natural Language Processing (NLP). One of the long-term goals of the AI research community is to further develop NLP in such a way that artificial intelligence will be able to interpret human communication and interactions so well that systems can formulate answers to queries independently and contextually. This stage of development is referred to as Natural Language Understanding (NLU).

Thanks to NLU, AI systems could in future provide answers based on the analysis of contextual information. For example, a voice assistant on a mobile device could use GPS information not only to infer the relevance of certain place names, but also that the environment inspires the user to change the topic ("Do we have partner companies in the logistics sector in this area?"). To achieve this, scientists still have a number of challenges to overcome. These include the development of an interface between unstructured data such as verbal statements, but also tweets and comments in social media on the one hand and structured data such as that available in tables or databases on the other.

The development of such an interface between language and structured knowledge is the aim of the three-year cooperation project entitled "Language-Knowledge Interaction" between the Institute for Machine Language Processing at the University of Stuttgart and IBM Research Europe.

"Perhaps the most striking feature of human language is that its expressions are like chameleons: They can adapt their meaning depending on the context. This allows people to be surprisingly concise when communicating complex issues - even in rapidly changing contexts. Natural Language Understanding systems have to find clues in speech and text that point to the correct interpretation contexts," says Jonas Kuhn, Professor of Computational Linguistics at the University of Stuttgart and head of the project on the university side. "Deep learning methods are now able to recognize relevant patterns in training data. But it is still a major challenge to go beyond learning the right solutions for a very specific task. Many application scenarios require systems that can generalize and provide a rationale for the decisions made."

"As part of the AI Horizons Network, IBM researchers are working with world-class faculty and brilliant students on a series of ambitious research projects and experiments designed to accelerate the application of AI to bring value to society," says Dr. Anika Schumann, Manager of Artificial Intelligence at IBM Research and responsible for the project on the company's side. "The results of this collaboration have the potential to influence and change the application of AI in areas as diverse as healthcare, materials science and finance."

The network's projects are aimed at applying different uses of AI in areas such as health, the environment, logistics and education. The network deals with the entire so-called AI stack, from the analysis of the unstructured and structured data required to train the systems to the development of novel computing infrastructures needed to optimize the new data-intensive workloads in a digital world.

The Knowledge-Language Interaction project will focus specifically on the development of an automated interface between unstructured and structured data using machine learning. Manually created translation rules are precise but limited to a fixed grid of distinctions. Thanks to recent advances in deep learning methods, it is now possible to automatically induce complex, multidimensional representations for text and language from the natural usage patterns in data.

The collaboration makes the University of Stuttgart the first institution in Europe to join the IBM AI Horizons Network. Leading universities around the world such as the Massachusetts Institute of Technology (MIT), IIT Bombay, Université de Montreal and University of Massachusetts at Amherst work together with IBM within the network. as