Paper 1: An Ontology-driven DBpedia Quality Enhancement to Support Entity Annotation for Arabic Text
Abstract: Improving NLP outputs by extracting structured data from unstructured data is crucial, and several tools are available for the English language to achieve this objective. However, little attention has been paid to the Arabic language. This research aims to address this issue by enhancing the quality of DBpedia data. One limitation of DBpedia is that each resource can belong to multiple types and may not represent the intended concept. Additionally, some resources may be assigned incorrect types. To overcome these limitations, this study proposes creating a new ontology to represent Arabic data using the DBpedia ontology, followed by an algorithm to verify type assignments using the resource's title metadata and similarity between resources' descriptions. Finally, the research builds an entity annotation tool for Arabic using the verified dataset.
Keywords: Entity annotation; semantics annotation; DBpedia; Arabic language; ontology; semantic web; linked open data