DBpedia Spotlight uses structured information extracted from Wikipedia to perform information extraction from text. On the one hand, disambiguations, redirects, entity types and entity properties are invaluable to complement natural language text in several information extraction tasks such as entity linking and relationship extraction. On the other hand, results from these information extraction tasks can be employed as suggestion engines that help users to provide more complete and interconnected encyclopaedic knowledge. This synergistic cycle is likely to figure both as productivity booster (more results with less effort) and as incentive for all involved parts to increase their participation (easier to find where to put effort).
Wikimedia Policies, Ethics, and Human Subjects ProtectionEdit
Benefits for the Wikimedia communityEdit
Pablo N. Mendes, Max Jakob, Andrés García-Silva and Christian Bizer. DBpedia Spotlight: Shedding Light on the Web of Documents. In the Proceedings of the 7th International Conference on Semantic Systems (I-Semantics). Graz, Austria, 7–9 September 2011. (to appear)