Leibniz MMS Days 2020 - Abstract
Scholarly information is traditionally published in prosaic articles, optimised for human cognition. Our vision for the Open Research Knowledge Graph (ORKG) is the supplementary processing of selected parts of this information into machine actionable data. The structural science mathematics provides particularly suitable content for the ORKG: Its published prose is clear and dense from a linguistic point of view; many formulae are already machine interpretable to some extent. In a first step, we ingest into the ORKG operational research literature reviews that compare (numerical) methods to solve optimisation problems against one another. Subsequently, we generate queries to retrieve the structured information again in a semantically sensible way.