1 / 28

FAO Ontology Portal Prototype FISHERY

FAO Ontology Portal Prototype FISHERY. January 2004. Development of Multilingual Domain Ontologies Fishery Ontology. The goal Making information interchangeable between ASFA, FIGIS, OneFish and Agrovoc The approach

deana
Download Presentation

FAO Ontology Portal Prototype FISHERY

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. FAOOntology Portal Prototype FISHERY January 2004

  2. Development of Multilingual Domain Ontologies Fishery Ontology • The goal • Making information interchangeable between ASFA, FIGIS, OneFish and Agrovoc • The approach • Creating an ontology, integrating or mapping the 3 different systems + Agrovoc • Linking of the Ontology through wrappers to the different Information Systems

  3. strains Species life cycle diseases Farming technique Hatchery technique Spawning technique Health monitoring technique Breeding technique Expl. form Environment Aquaculture Resource Farming system Production center Water Area land Regulation suppliers management system Institution Fishery OntologyCreation of the core ontology OneFish FIGIS AGROVOC ASFA

  4. Fishery Ontology: snapshot

  5. Fishery OntologyReconcile different vocabularies “navire de pêche”, “fishing vessel”, “embarcaciones de pesca” AGROVOC or ASFA or other “fishing vessels,” “fishing boat,” AGROVOC: “ships” ASFA: “fishing vessels”

  6. Ontology Portal: Functionalities • Form versus meaning: • Traditional Search • Concept Search • Implemented functionalities: • synonym search • multilingual capability • terminology brokering • disambiguation • related concepts • query expansion • Basic natural language queries • Semantic navigation of bibliographical metadata • Semantic Navigation of Knowledge • Alphabetic list ... as a starting point • Core Fishery Concepts ... as a starting point

  7. Additional Functionalities Functionalities to further develop: • Intelligent query expansion • Natural language queries (paraphrasing) • check spelling • parsing • stemming • Semantic Navigation of Knowledge • Thesaurus based

  8. Demo

  9. 1) Form versus meaning: a) Traditional Search The system gets records from different portals using the stringvessel

  10. Using a free text search, the system retrieves all records containing the string “vessel” including records not pertinent to the user’s intended meaning of the term 1) Form versus meaning: a) Traditional SearchFAOBIB results Using a keyword search, the system retrieves 0 results as the thesaurus used in this portal does not use vessel as a keyword

  11. 1) Form versus meaning: b) Concept Search • In a concept based search the system retrieves all meanings represented by the term vessel. • For example: • vessel can refer to the concept blood vessel • vessel can also be interpreted as ship

  12. 2) Implemented functionalities: a) synonym search The same records will be retrieved regardless of the specific synonyms or singular/plural forms that the user uses to refer to a concept.

  13. 2) Implemented functionalities: b) multilingual capability The system is also able to understand a concept even when different languages are used.

  14. 2) Implemented functionalities: c) terminology brokering User query terms are converted into the respective corresponding variants used in a given information system

  15. 2) Implemented functionalities: d) disambiguation When the query term is ambiguous all concepts that correspond to that term are displayed to the user and disambiguated using the parent concept

  16. 2) Implemented functionalities: e) related concepts Concepts related to the user query are displayed (e.g. for query refinements, etc.)

  17. 2) Implemented functionalities:f) query expansion (ex. 1) The query can be refined using one or more related concept(s)

  18. 2) Implemented functionalities:f) query expansion (ex. 2) To improve query results (in terms of quality and quantity), it is possible to select one or more translations or related terms...

  19. ...The query will then take into consideration all selected lexicalizations to improve the query. The system will broker the refined query using the terms from a given portal..

  20. 3) Basic natural language queries Bibliographical records related to fishing vessel in Kenya

  21. 4) Semantic navigation of bibliographical metadata

  22. 5) Semantic Navigation of Knowledge: a) Alphabetic list ... as a starting point

  23. 5) Semantic Navigation of Knowledge: b) Core Fishery Concepts ... as a starting point parent concept(s) children concept(s)

  24. Additional Functionalities

  25. a) Intelligent query expansion • “japanese fishing vessel” • The system search for documents related to Japan and fishing vessel • If 0 results are retrieved, the system search for Asia and fishing vessel • etc.

  26. b) Natural language queries (paraphrasing) • “japanese fishing vessel” • “tuna ships in the Caribbean sea” • etc. • The System check first for spelling errors, parse the query

  27. c) Semantic Navigation of Knowledge: a) Thesaurus based Highlighting the originator thesaurus. User can select a specific thesaurus to look for.

  28. Further implementation • Improved natural language processing • Language recognition • Improved parsing (combinatorial) • Extended concept resolution • Intelligent query expansion • Inferencing • Machine learning • Display of results • Clustering • Ranking

More Related