Knowledge Tagger enables its users to perform Named Entity Resolution in texts using relevant domain ontologies and semantic data. Its distinguishing characteristic is its customization capabilities as it allows users to define and apply Ontology-Based Disambiguation Evidence Models, based on their knowledge about the domain(s) and expected content of the texts to be analyzed.
To construct an evidence model the user needs to do only two things: i) Determine the concepts whose instances wants to detect/disambiguate and ii) determine the related to them concepts whose instances may serve as contextual disambiguation evidence within the expected texts. Having done that, he/she may automatically generate a disambiguation model and immediately apply it to relevant texts.
P. Alexopoulos, B. Villazon-Terrazas, J.M. Gómez-Pérez (2013) “Knowledge Tagger: Customizable Semantic Entity Resolution using Ontological Evidence”, Demo at the 9th International Conference on Semantic Systems (I-SEMANTICS), Graz, Austria, September 4-6, 2013.
P. Alexopoulos, C. Ruiz, J.M. Gómez-Pérez (2012), “Scenario-Driven Selection and Exploitation of Semantic Data for Optimal Named Entity Disambiguation”, Proceedings of the 1st Semantic Web and Information Extraction Workshop (SWAIE 2012), Galway, Ireland, October 8-12, 2012.