Image Browsing and Natural Language Paraphrases of Semantic Web Annotations

Abstract : Recently, there has been interest in marking up digital images with annotations describing the content of the images using Web-based ontologies encoded in the W3C's Web Ontology Language (OWL). The annotations are subsequently exploited to improve the user experience of large collections of images, whether by enhanced search or by a structured browsing experience. In the latter case, the complexity and unfamiliarity of logic-based ontology languages may do more to impede, than aid, the user. To alleviate this problem, the authors propose using automatic generation of natural language (NL) paraphrases of OWL statements to assist browsing image content. In this paper, they provide an overview of their NL generation approach and an empirical evaluation of the use of their paraphrases for image browsing.