Thumbnail Image

Requirements for the treatment of multilinguality in ontologies within FAO








Also available in:
No results found.

Related items

Showing items related by metadata.

  • Thumbnail Image
    Book (stand-alone)
    A Comprehensive Framework for Building Multilingual Domain Ontologies: Creating a Prototype Biosecurity Ontology 2002
    Also available in:
    No results found.

    This paper presents our ongoing work in establishing a multilingual domain ontology for a biosecurity portal. As a prototypical approach, this project is embedded into the bigger context of the Agricultural Ontology Service (AOS) project of the Food and Agriculture Organization (FAO) of the UN. The AOS will act as a reference tool for ontology creation assistance and herewith enable the transfer of the agricultural domain towards the Semantic Web. The paper focuses on introducing a comprehensive, reusable framework for the process of semi-automatically supported ontology evolvement, which aims to be used in follow-up projects and can eventually be applied to any other domain. Within the multinational context of the FAO, multilingual aspects play a crucial role and therefore an extendable layered ontology modelling approach will be described within the framework. The paper will present the project milestones achieved so far: the creation of a core ont ology, the semiautomatic extension of this ontology using a heuristic toolset, and the representation of the resulting ontology in a multilingual web portal. The reader will be provided with a practical example for the creation of a specific domain ontology, which can be applied to any possible domain. Future projects, including automatic text classification, and ontology facilitated search opportunities, will be addressed at the end of the paper.
  • Thumbnail Image
    Book (stand-alone)
    Ontology-based navigation of bibliographic metadata: example of the Food, Nutrition and Agriculture Journal 2007
    Also available in:
    No results found.

    This paper describes the work done within the Food and Agriculture Organization of the United Nations (FAO) on providing an ontology-based navigation to the Food, Nutrition and Agriculture (FNA) Journal. The aim of the revised navigation was to provide more efficient and effective browsing of the Food and Nutrition Publications using a knowledge model to guide the user with concepts and relationships relevant to a specific subject area. With this approach, data from two different bibliographica l databases were reused, by merging and unifying them and make them better accessible to users. A preliminary metadata merge was needed to combine all the information into one system in order to produce a metadata-ontology. Resource Description Framework Schema (RDFS) has been chosen to exploit semantic relationships e.g. the possibilities of browsing the data in different ways (by keywords, categories, authors, etc.), and the creation of a multilingual concept-based advanced search.
  • 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.

Users also downloaded

Showing related downloaded files

No results found.