Fabrizio Orlandi

“DynamoKG” Exploring dynamic and uncertain facts in knowledge graphs

Knowledge graphs (KGs) have gained increasing popularity over the last years, especially in industry where they are now at the core of relevant consumer products (e.g. Google and Bing search engines). According to a recent business report, “51 percent of global data and analytics technology decision makers are either implementing, have already implemented, or are upgrading their graph databases”. KGs are knowledge-bases of facts about entities and concepts (e.g., places, persons, artifacts) which are represented using the flexible structure of a graph. Facts are often extracted from encyclopedic knowledge, such as Wikipedia, or existing structured repositories (e.g. Wikidata), or even from unstructured sources such as social media posts (e.g. Facebook Graph). For example, a KG containing information about organisations is likely to include facts about companies, their founders, key persons, headquarters’ locations, number of employees, etc. However, facts related to entities or concepts that are dynamically changing over time are usually missing or outdated. The evolving dynamics of real world events are usually not reflected into knowledge bases. Hence, current repositories tend to represent only static snapshots of real world entities, ignoring their changes over time.