Generation of multilingual personalized environmental bulletins from an OWL-based ontology

In this paper, we tackle the problem of generation of user-oriented multilingual environmental information from ontologies in the context of a personalized environmental decision support service. We present a unified multiple layer ontology framework modeled in OWL that consists of three ontology layers: the domain ontology, the domain communication ontology, and the communication ontology. The domain ontology contains factual application-neutral concept configurations and relations. The domain communication ontology models data aggregation, qualitative interpretation of numerical data, user tailored warnings and recommendations triggered by an environmental condition given in a specific context, etc., while the communication ontology specifies knowledge needed for the tasks involved in the generation process, and is populated using a pipeline of SPARQL queries. We show how a large scale instantiation of this framework in the environmental domain serves multilingual NLG.