Zablith, Fouad; d'Aquin, Mathieu; Sabou, Marta and Motta, Enrico
PDF (Version of Record)
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
|Google Scholar:||Look up in Google Scholar|
The tasks of learning and enriching ontologies with new concepts and relations have attracted a lot of attention in the research community, leading to a number of tools facilitating the process of building and updating ontologies. These tools often discover new elements of information to be included in the considered ontology from external data sources such as text documents or databases, transforming these elements into ontology compatible statements or axioms. While some techniques are used to make sure that statements to be added are compatible with the ontology (e.g. through conflict detection), such tools generally pay little attention to the relevance of the statement in question. It is either assumed that any statement extracted from a data source is relevant, or that the user will assess whether a statement adds value to the ontology. In this paper, we investigate the use of background knowledge about the context where statements appear to assess their relevance. We devise a methodology to extract such a context from ontologies available online, to map it to the considered ontology and to visualize this mapping in a way that allows to study the intersection and complementarity of the two sources of knowledge. By applying this methodology on several examples, we identified an initial set of patterns giving strong indications concerning the relevance of a statement, as well as interesting issues to be considered when applying such techniques.
|Item Type:||Conference Item|
|Copyright Holders:||2009 The Authors|
|Academic Unit/Department:||Knowledge Media Institute|
|Interdisciplinary Research Centre:||Centre for Research in Computing (CRC)|
|Depositing User:||Kay Dave|
|Date Deposited:||21 Oct 2010 12:10|
|Last Modified:||25 Feb 2016 13:01|
|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.