The Data Science (DICE) group develops methods, algorithms and applications for the extraction, integration, storage, querying, access and consumption of large-scale datasets. In contrast to most other groups, DICE focusses on knowledge-driven methods. We hence rely and extend on knowledge representation standards developed for the Semantic Web. The area of application of our research include but are not limited to solutions for federated queries on the Web, knowledge extraction from text and other types of datasets, knowledge integration and fusion, keyword-based search and question answering.

We are dedicated to open-source software and open publications. Have a look at our tool page to find a list of the open-source frameworks we offer. These tools and frameworks implement our innovative approaches to the problems aforementioned and are designed to facilitate their swift integration into industry projects. Our project page gives you an overview of the projects we have worked or are working on. Interested in working with us? Please click here to contact us.

Funded by


The third LIMBO (https://www.limbo-project.org/) face to face meeting happened on June 20th in Berlin at BMVI, the Federal Ministry of Transport and Digital Infrastructure.

The accompanying WIK...

Read more

On 19th June 2018, Erwin Hermann presented the research project SOLIDE at the BMBF Innovation Forum "Civil Security" 2018 as part of the session "Operational support - Better management of crisis...

Read more

If you happen to be a data enthusiast and find yourself in Berlin this weekend, don’t miss out on the PyData Conference which will take place in Charite Campus, Augustenburger Platz 1!

Witness some...

Read more

Geospatial data is vital for many application scenarios, such as navigation, logistics, and tourism. At the same time, a large number of currently available datasets (both RDF and conventional)...

Read more

The goal of Question Answering over Knowledge Bases (KB) is to provide short and crisp answers to natural language questions. A KB-QA system performs this by first translating the user’s question to a...

Read more

Named Entity Recognition and Entity Linking systems are very useful for extracting data into machine understandable form. Several such systems have been developed in recent years, but how good are...

Read more


Prof. Dr. Axel-Cyrille Ngonga Ngomo
head professor
phone: +49 5251 60-3342
fax: +49 5251 60-3436
e-mail: axel.ngonga(at)upb.de
office: O4.213
Simone Auinger
phone: +49 5251 60-1764
fax: +49 5251 60-3436
e-mail: mone(at)upb.de
office: O 4.113