Williams, Sandra; Third, Allan and Power, Richard
Due to copyright restrictions, this file is not available for public download
Click here to request a copy from the OU Author.
|Google Scholar:||Look up in Google Scholar|
The SWAT TOOLS ontology verbaliser generates a hierarchically organised hypertext designed for easy comprehension and navigation. The document structure, inspired by encyclopedias and glossaries, is organised at a number of levels. At the top level, a heading is generated for every concept in the ontology; at the next level, each entry is subdivided into logically-based headings like ‘Definition’ and ‘Examples’; at the next, sentences are aggregated when they have parts in common; at the lowest level, phrases are hyperlinked to concept headings. One consequence of this organisation is that some statements are repeated because they are relevant to more than one entry; this means that the text is longer than one in which statements are simply listed. This trade-off between organisation and brevity is investigated in a user study.
|Item Type:||Conference Item|
|Copyright Holders:||2011 Association for Computational Linguistics|
|Project Funding Details:||
|Extra Information:||Proceedings of the 13th European Workshop on Natural Language Generation (ENLG),
Nancy, France, September 2011.
|Academic Unit/Department:||Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
|Interdisciplinary Research Centre:||Centre for Research in Computing (CRC)|
|Depositing User:||Sandra Williams|
|Date Deposited:||07 Oct 2011 08:05|
|Last Modified:||04 Oct 2016 19:47|
|Share this page:|