Stevens, Robert; Malone, James; Williams, Sandra and Power, Richard
(2010).
![[img]](http://oro.open.ac.uk/style/images/fileicons/application_pdf.png)
|
PDF (Version of Record)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (188Kb) |
| Google Scholar: | Look up in Google Scholar |
|---|
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.
| Item Type: | Conference Item |
|---|---|
| Copyright Holders: | 2010 The Authors |
| Academic Unit/Department: | Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications Faculty of Science, Technology, Engineering and Mathematics (STEM) |
| Interdisciplinary Research Centre: | Centre for Research in Computing (CRC) |
| Item ID: | 21501 |
| Depositing User: | Sandra Williams |
| Date Deposited: | 13 Jul 2010 10:56 |
| Last Modified: | 06 Aug 2016 23:26 |
| URI: | http://oro.open.ac.uk/id/eprint/21501 |
| Share this page: |     |
Download history for this item
These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.