Copy the page URI to the clipboard
Stevens, Robert; Malone, James; Williams, Sandra and Power, Richard
(2010).
Abstract
Text definitions for entities within bio-ontologies are a cor-nerstone of the effort to gain a consensus in understanding and usage of those ontologies. Writing these definitions is, however, a considerable effort and there is often a lag be-tween specification of the entities in the ontology and the development of the text-based definitions. As well as these text definitions, there can also be logical descriptions and definitions of an ontology's entities. The goal of natural lan-guage generation (NLG) from ontologies is to take the logi-cal description of entities and generate fluent natural lan-guage. We should be able to use NLG to automatically pro-vide text-based definitions from an ontology that has logical descriptions of its entities and thus avoid the bottleneck of authoring these definitions by hand. In this paper we present some early work in using NLG to provide such text definitions for the Experimental factor Ontology (EFO). We present our results, discuss issues in generating text definitions, and highlight some future work.