RoundTrip Ontology Authoring

Controlled Language (CL) for Ontology Editing tools offer an attractive alternative to naive users, wishing to create Ontologies. However despite the benefits of CLs, users are still required to learn the correct syntactic structures in order to use the Controlled Language properly. Referring to CL vocubulary/syntax rules can be time consuming, annoying and in certain cases may prevent uptake of the tool. This paper extends work based on a controlled language for ontology editing CLOnE, which uses standard NLP tools, for processing the language and manipulating an ontology. The reversal of this process involves text generation of the CLOnE language from an existing ontology using Natural Language Generation (NLG), specifically template based/shallow NLG. The text generator and the CLOnE authoring process both combine to form a RoundTrip Ontology Authoring environment: one can start with an existing imported ontology or one originally produced using CLOnE, (re)produce the Controlled Language using the NL generator, modify or edit the text as required and subsequently parse the text back into the ontology using the CLOnE environment. Building on previous methodology we undertook an evaluation, comparing the Round Trip Ontology Authoring process with a well-known ontology editor; Where previous work required a CL reference manual with several examples in order to use the controlled language, the substitution of NLG reduces this learning curve for users, while simultaneously improving upon existing results for basic Ontology editing tasks.