Semantic Web
The Data Science Chair researches semantic relations in the web and the real world. Relations exist for example between objects (the apple is in the basket), persons (Tom and Annie are friends) and general concepts (dogs are canines) and may be leveraged from different sources: link networks, hashtags, text, tags or user behaviour. We develop new methods to extract and classify semantic entities and relations and utilize them to build ontologies, which in turn can be applied to various tasks like language recognition or question answering systems.
Projects
We are currently working on the following projects:
Selected Publications
Here is a list of selected publications. You can find the full list here.
-
ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings. Hettinger, Lena; Dallmann, Alexander; Zehe, Albin; Niebler, Thomas; Hotho, Andreas (2018).
-
Ontologies Improve Text Document Clustering. Hotho, A.; Staab, S.; Stumme, G. (2003). 541–544.
-
Discovering Shared Conceptualizations in Folksonomies. Jäschke, Robert; Hotho, Andreas; Schmitz, Christoph; Ganter, Bernhard; Stumme, Gerd in Web Semantics: Science, Services and Agents on the World Wide Web (2008). 6(1) 38–53.
-
Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning. Niebler, Thomas; Becker, Martin; Pölitz, Christian; Hotho, Andreas (2017).
-
Extracting Semantics from Unconstrained Navigation on Wikipedia. Niebler, Thomas; Schlör, Daniel; Becker, Martin; Hotho, Andreas in KI (2016). 30(2) 163–168.