Thumbnail Image

From thesauri to Ontologies: A short case study in the food safety area in how ontologies are more powerful than thesauri From thesauri to RDFS to OWL

From thesauri to RDFS to OWL








Also available in:
No results found.

Related items

Showing items related by metadata.

  • Thumbnail Image
    Book (stand-alone)
    Automatic Term Relationship Cleaning and Refinement for AGROVOC 2005
    Also available in:
    No results found.

    AGROVOC is a multilingual thesaurus developed and maintained by the Food and Agricultural Organization of the United Nations. Like all thesauri, it contains some explicit semantics, which allow it to be transformed into an ontology or used as a resource for ontology construction. However, most thesauri, AGROVOC included, give very broad relationships that lack the semantic precision needed in an ontology. Many relationships in a thesaurus are incorrectly applied or defined too broadly. According ly, extracting ontological relationships from a thesaurus requires data cleaning and refinement of semantic relationships. This paper presents a hybrid approach for (semi-)automatically detecting these problematic relationships and for suggesting more precisely defined ones. The system consists of three main modules: Rule Acquisition, Detection and Suggestion, and Verification. The Refinement Rule Acquisition module is used to acquire rules specified by experts and through machine learning. The Detection and Suggestion module uses noun phrase analysis and WordNet alignment to detect incorrect relationships and to suggest more appropriate ones based on the application of the acquired rules. The Verification module is a tool for confirming the proposed relationships. We are currently trying to apply the learning system with some semantic relationships to test our method.
  • Thumbnail Image
    Book (stand-alone)
    Pruning-based identification of domain ontologies 2003
    Also available in:
    No results found.

    We present a novel approach of extracting a domain ontology from large-scale thesauri. Concepts are identified to be relevant for a domain based on their frequent occurrence in domain texts. The approach allows to bootstrap the ontology engineering process from given legacy thesauri and identifies an initial domain ontology that may easily be refined by experts in a later stage. We present a thorough evaluation of the results obtained in building a biosecurity ontology for the UN FAO AOS project .
  • Thumbnail Image
    Document
    A Practical Approach on Creating a Restricted Ontology for Crop Wild Relatives
    CWR ontology. Project report
    2007
    Also available in:
    No results found.

    The task to identify a subset of about 400 terms highly relevant to crop wild relatives was performed as a continuation to an earlier project where a set of about 11400 term was extracted from on-line sources. Terms with high relevance were grouped into themes, roughly corresponding to Agrovoc (top level) categories, or indicatives of the thematic sources from which the terms were collected (biological, geographical on-line dictionaries etc), with an attempt to balance the number of terms betw een the groups. For the import into the ontology structure the themes were converted to namespaces in order to preserve the grouping and allow manipulation within ontology client programs on terms based on namespace grouping. Before the import the namespaces were slightly modified and adapted to some other existing ontologies. In addition to selecting relevant terms and definitions, definition of vertical and horizontal relationships between the terms was performed. Terms were also linked to s ources (uris) through Dublin Core extensions of the ontology structure. The export from sql to rdf/owl was done with a script written in Perl that extracted the terms, descriptions, sources from the database, plus vertical hierarchy, term synonyms and other variants, as well as some simple horizontal relationships and produced an import file for Protégé in rdf/owl format. The resulting subset of terms was provided as a number of files; a main file containing core structure, object and da ta type definitions and term data in separate files per namespace, suitable for import by an ontology client program such as Protégé.

Users also downloaded

Showing related downloaded files

No results found.