According to Viviana Rojas de Amon, Digital Marketing Professional at Semantic Web Company GmbH, knowledge graphs (KGs) can be divided into two categories — expert and general purpose KGs. One of the differences is that the expert KGs have strict knowledge accepted by domain experts. Whereas for general purposes, KGs need a vast amount of common sense knowledge that is provided by non-expert users that is not necessarily strictly validated. This blog post discusses a new innovative crowdsourcing approach to extend general-purpose knowledge graphs based on a human-in-the-loop model.
The novel crowdsourcing approach uses automatic reasoning mechanisms inspired by belief-revision. It incorporates views of different users, extracts the largest subgraph without the contradictions and integrates it into the KG. In addition, users who do not have expertise in the knowledge contained in the graph can give their updates intuitively.
There are many other benefits of employing this approach. For instance, users can work directly with the hierarchy of classes, but not with any other entities. It is suitable for large KGs because contributors without expertise in the existing knowledge can offer their inputs. In addition, the reasoning mechanisms of the semantic web are used to analyze the inputs, estimate its value and avoid contradictions.
Click here to continue reading how this approach tackles the challenges inherent in crowdsourcing taxonomies directly.
Please give your feedback on this article or share a similar story for publishing by clicking here.
