A Question Answering System for retrieving German COVID-19 data driven and quality-controlled by Semantic Technology
Keywords: Question Answering, User Interaction, COVID-19
TL;DR: A component-based question answering system using RDF at its core implemented to provide official COVID-19 data that is quality-controlled via SPARQL.
Abstract: The COVID-19 pandemic is a showcase for a data-driven society. However, making the corresponding data available is not easy due to local characteristics and time-depending metrics. We present the Coronabot facilitating the access to German COVID-19 data capable of answering German and English questions. The component-based system is capable of understanding questions relating time and (even small) places in Germany. It is driven by RDF as all internal component interact with each other using RDF. Therefore, we are enabled to microbenchmark the component using SPARQL and therefore prove the quality requirements.