GeneratingNaturalLanguageDescriptionsfromOWLOntologies:A DetailedPresentationoftheNaturalOWLSystem
Ion Androutsopoulos, Γεράσιμος Λάμπουρας, Dimitrios Galanis · 2012
We present Naturalowl, an open-source natural language generation system that produces texts describing individuals (e.g., products, museum exhibits) or classes of individuals from owl ontologies optionally associated with linguistic and user modeling resources. Unlike simpler owl verbalizers, which typically express a single axiom of the ontology at a time in controlled and often not entirely uent natural language mostly for the benet of domain experts, we aim to generate uent, coherent, and interesting multi-sentence texts appropriate for end-users (e.g., customers, museum visitors). A key benet of using a system like Natural owl on the Semantic Web is that it becomes possible to publish information in the form of owl ontologies, and rely on natural language generation to automatically produce personalized texts in multiple languages from the ontologies, thus making the information easily accessible not only to computer programs and domain experts, but also to end-users. We discuss Naturalowl’s processing stages of generating texts, the optional domain-specic linguistic and user modeling resources that can be used at each stage, why such resources are useful, and how they can be created and represented. We also report on trials we performed to measure the eort that is required to congure Natural owl for new ontologies, and the quality of the resulting texts.