Vizualizing and Verbalizing Class Expressions

Project Group Master

Visualizing and Verbalizing Class Expressions

With the ever-growing generation of data for the Semantic Web comes an increasing demand for this data to be made available to non-semantic Web experts. This non-trial goal can be achieved by (1) visualizing class expressions or (2) translating class expressions into natural language. Although LD2NL (github-repo) can be used for (2), there are no tools developed for (1). The goal of this project is to

Create a web application that receives inputs containing class expressions and additional data (e.g. F1 score). Such inputs are visualized, verbalized and shown to users. By this, users are informed about the current process of class expression problem in a fashion akin to the TensorBoard.

Integrate this web application into one of our existing frameworks, e.g. ontolearn or DRILL.

Literature

"A Holistic Natural Language Generation Framework for the Semantic Web" Axel-Cyrille Ngonga Ngomo, Diego Moussallem, Lorenz Buhmann

Project presentation

The slides of the presentation can be found here.

Question & Answer Session

In case you have further questions, feel free to contact Michael Röder.