A comprehensive framework for building multilingual domain ontologies
Upcoming SlideShare
Loading in...5
×
 

Like this? Share it with your network

Share

A comprehensive framework for building multilingual domain ontologies

on

  • 614 views

 

Statistics

Views

Total Views
614
Views on SlideShare
614
Embed Views
0

Actions

Likes
0
Downloads
3
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment
  • Java knowledge needed for customizing API = Application Programming interface
  • Examples/explaining Codex/SPS SPS = The WTO Agreement on the Application of Sanitary and Phytosanitary Measure Codex = contains food standards
  • IPPC = International Plant Protection Convention: Standards to Plant Health OIE = Organization International des Epizooties (Int. Org. for Animal Health) – Standards for Animal Health

A comprehensive framework for building multilingual domain ontologies Presentation Transcript

  • 1. A Comprehensive Framework for Building Multilingual Domain Ontologies : Creating an ontology on Food Safety, Animal and Plant Health (OFsAPH) Boris Lauser Nordic AOS Workshop: Copenhagen 28 th February 2003
  • 2. Agenda
    • Introduction:
      • Why: The Biosecurity Portal Project
      • How: The modeling approach
    • Framework for ontology creation
    • Application of framework :
      • Creation of the Food Safety Ontology
    • Outlook:
      • Application scenario
    • Discussion
    Introduction Framework Application Outlook Discussion
  • 3. The IP-FsAPH International Portal on Food Safety, Animal and Plant Health
    • access point for official national and international information on biosecurity
    • interdisciplinary approach
    • integrated access to information in the 3 areas
    • global public access
    • controlled access to nationally nominated users
    Currently available on: http://193.43.36.96/servlet/CDSServlet Introduction Framework Application Outlook Discussion
  • 4. The IP-FsAPH International Portal on Food Safety, Animal and Plant Health Introduction Framework Application Outlook Discussion
    • Provides access to large amounts of data, coming from various resources from all over the world
    • Need to make this data available and searchable through the portal
    • Realization by exposing metadata
    • Need for controlled, commonly agreed on subject vocabulary
    • Integration of an ontology to provide the necessary controlled vocabulary and semantics which can be explored for enhanced information retrieval
  • 5. Introduction Framework Application Outlook Discussion KAON The Karlsruhe Ontology and Semantic Web Tool Suite KAON is an open-source ontology management infrastructure
    • Major Components:
    • OIModeler : tool for ontology creation and evolution
    • KAON Portal : a web based portal for browsing KAON ontologies
    • KAON API: a programming API to access the ontology independently from any storing mechanism
    • Engineering Server: ontology storage mechanism based on relational databases to provide concurrent access and scalability
    • Text-To-Onto: Semiautomatic ontology creation using text mining techniques
    Freely available on: http://kaon.semanticweb.org
  • 6. The Generic RDFS model: Introduction Framework Application Outlook Discussion
  • 7. The KAON modeling approach Introduction Framework Application Outlook Discussion The KAON lexical model extension:
  • 8.
    • Introduction:
      • Why: The Biosecurity Portal Project
      • How: The modeling approach
    • Framework for ontology creation
    • Application of framework :
      • Creation of the Food Safety Ontology
    • Outlook:
      • Application scenario
    • Discussion
    Introduction Framework Application Outlook Discussion Agenda
  • 9. The framework A comprehensive framework for building a domain ontology Focus : Concept acquisition and development of the lifecycle of ontology creation Introduction Framework Application Outlook Discussion
  • 10. The framework: 5 phases
    • Resource selection
    • Semiautomatic ontology concept acquisition
      • Creation of a core ontology from scratch
      • Reuse of existing vocabularies
    • Merging of ontologies
    • Extension and refinement
    • Evaluation
    Introduction Framework Application Outlook Discussion
  • 11. The Framework: overview Core ontology Manual creation Focused Web crawling List of domain start web pages List of frequent terms List of domain Specific documents Term BT t1 NT t2 RT t3 Term USE t3 … Thesaurus RDFS ontology model convert Ontology pruning and learning algorithm Domain corpus Generic corpus Pruned ontology List of critical concepts Manual creation of core ontology 1 st acquisition approach 2 nd acquisition approach Text To Onto Introduction Framework Application Outlook Discussion Semi- automatic Ontology Acquisition Merging of ontologies Refinement and Extension Evaluation Selection of resources
  • 12. Agenda
    • Introduction:
      • Why: The Biosecurity Portal Project
      • How: The modeling approach
    • Framework for ontology creation
    • Application of framework :
      • Creation of the Biosecurity Ontology
    • Outlook:
      • Application scenario
    • Discussion
    Introduction Framework Application Outlook Discussion
  • 13. Manual creation of core ontology Application of the framework: 1 st iteration Introduction Framework Application Outlook Discussion 1 st iteration Semi- automatic Ontology Acquisition Merging of ontologies Refinement and Extension Evaluation Selection of resources
  • 14. Phase 1 : Selection of Resources/ Manual creation of core ontology 67 concepts 91 relationships
    • Information Resources:
    • Brainstorming
    • Codex Alimentarius
    • SPS Agreement
    Core Ontology Ontology Editor (OIModeler) 3 subject specialists Introduction Framework Application Outlook Discussion 1 st iteration
  • 15. Phase 2: 1 st Acquisition Approach: Focused Crawling Focused Web Crawling 68 concepts 91 relationships Core Ontology List of extracted main sites: http:// www.foodsafety.gov / Gateway to Government Food Safety Information http:// vm.cfsan.fda.gov / Center for Food Safety & Applied Nutrition http:// www.inspection.gc.ca / Canadian Food Inspection Agency http:// www.extension.iastate.edu/foodsafety / Iowa State University - Food Safety Project http:// www.foodsafety.iastate.edu Iowa State University - Food Safety Consortium http:// www.fsis.usda.gov / United States Department of Agriculture, Food Safety and Inspection Service http:// www.nal.usda.gov/foodborne/index.html Foodborne Ilness Education Information Center http:// www.euro.who.int/foodsafety World Health Organization – Regional Office for Europe Food Safety Programme List of 257 food Safety domain web pages Grouping into Main sites Introduction Framework Application Outlook Discussion 1 st iteration
  • 16. Selection of Documents
    • Domain Set: Manual selection
      • 11 documents
        • Codex Alimentarius: Description, Code of Ethics, Food Hygiene, Food Import and Export
        • Report of consultation on risk assessment of microbiological hazards in foods
        • Ensuring food quality and safety, Protecting food quality and safety
    • Domain Set: Focused Crawler Output
      • 5 documents extracted:
        • http://vm.cfsan.fda.gov/ ; http://www.inspection.gc.ca/ ; http://www.foodsafety.iastate.edu ; http://www.extension.iastate.edu/foodsafety/ ; http://www.euro.who.int/foodsafety
    • Generic documents: Manual Selection
      • 8 documents
        • www.nytimes.com
        • Several documents of the animal feed domain
    Introduction Framework Application Outlook Discussion 1 st iteration
  • 17. Phase 2: 2 nd Acquisition Approach: Thesaurus Pruning Food Safety Documents Generic Documents Rice BT … NT … RT … RT … RT … … AGROVOC 27365 keywords Automatic Pruning Extracted ontological structure: # of concepts: 504 taxonomic depth: 5 5 evaluation runs 1632 frequent terms Introduction Framework Application Outlook Discussion 1 st iteration
  • 18. Phase 3/4: Merging of Ontologies, Refinement 1632 Terms from pruning process 12 new concepts extracted Ontological structure extracted from AGROVOC 23 new concepts With hierarchical relationships extracted 67 concepts 91 relationships Core Ontology Assembly step 92 new relationships created Biosecurity Ontology Prototype 102 concepts 183 relationships Introduction Framework Application Outlook Discussion 1 st iteration
  • 19. Final Prototype Biosecurity Ontology Prototype 102 concepts 183 relationships 1.79 Core Ontology 67 concepts 91 relationships 1.36 Introduction Framework Application Outlook Discussion 1 st iteration relationships concept relationships concept
  • 20. 102 Concepts Agreement of Agriculture ALOP ALOP, Codex ALOP, OIE ALR animal byproducts animal diseases animal fats animal feed additives animal feed contaminants animal feed ingredients animal feeding animal health animal processing animal products animal waste animals antibiotics Bacteria bakery products biological agent CAC Caragene protocol CCFH cereal products cheese chemical agent Codex Committees commodities Consumer health diseases eggs exposure assessment fabrication FAO fishes food food additives food consumption food contaminants food export food import food ingredients food safety food-borne diseases fungi good hygienic practices hazard hazard characterization hazard identification human health human nutrition humans international agreements international food trade international governmental organizations IPPC labelling meat microorganisms microorganisms byproducts microorganisms processing microorganisms products microorganisms waste milk milk products milk products non-pathogens OIE packaging parasites pathogens physical agent plant byproducts plant diseases plant feed additives plant feed contaminants plant feed ingredients plant feeding plant health plant processing plant products plant waste plants processed animal products processed plant products processed products processing risk analysis risk assessment risk characterization risk communication risk management slaughter SPS agreement standards sugar TBT agreement transport viruses WHO WTO Introduction Framework Application Outlook Discussion 1 st iteration
  • 21. 29 Unique Relationships adopts adversely affect are included in are produced by are the source for can be used as constitutes describes determines ensures establishes govern has economical impact on Implies includes influences interacts with is a consequence of is a step in the process is comprised of is established by is protected by originate from refer to requires rule sustains trades uses Introduction Framework Application Outlook Discussion 1 st iteration
  • 22.
    • Open to users and subject specialists for evaluation
    • http://localhost:8080/faoportal/dispatcher
    Introduction Framework Application Outlook Discussion 1 st iteration Biosecurity Ontology Browser  Modified version of the KAON Portal Phase 5: Evaluation
  • 23. Application of the framework: 2 nd iteration Introduction Framework Application Outlook Discussion 2 nd iteration Semi- automatic Ontology Acquisition Merging of ontologies Refinement and Extension Evaluation Selection of resources
  • 24. Phase 1/2/3 : Resource selection, acquisition, merging Biosecurity Ontology Prototype 102 concepts 183 relationships Text To Onto ~ 100 domain Specific documents AGROVOC Revised Ontology Pruner List of frequent terms Pruned Agrovoc: ~ 3000 concepts Ontology Editor (OIModeler) Merging & Refinement 1 st acquisition approach 2 nd acquisition approach 2 nd iteration Introduction Framework Application Outlook Discussion
  • 25. Phase 4 : Extension and Refinement Biosecurity Ontology Core 2 nd iteration Introduction Framework Application Outlook Discussion Geographic Area Ontology Generic Properties Ontology Ontology on Food Safety, Animal and Plant Health
    • 3761 concepts
    • 16 unique relationships
    IPPC glossary
    • creation of a modular design for reusability
    Further Codex Alimentarius Classifications OIE classifications
  • 26. Agenda
    • Introduction:
      • Why: The Biosecurity Portal Project
      • How: The modeling approach
    • Framework for ontology creation
    • Application of framework :
      • Creation of the Biosecurity Ontology
    • Outlook:
      • Application scenario
    • Discussion
    Introduction Framework Application Outlook Discussion
  • 27. Application scenario : 2 use cases Use Case 1: Indexing the subject of a document Use Case 2: Searching information on the portal OFsAPH Indexer Searcher Introduction Framework Application Outlook Discussion Risk;… Subject Title … … Risk;… Search … …
  • 28. Ontology Enabled Search Application Display Ontology Metadata + Doc base Introduction Framework Application Outlook Discussion Search Results + Ontology Semantics KAON API Simple query Ontology semantics Enhanced query Found results Use Case 2: Ontology based search extension Search: Risk assessment Biosecurity Portal: … …
  • 29. Introduction Framework Application Outlook Discussion
  • 30. Introduction Framework Application Outlook Discussion
  • 31. Introduction Framework Application Outlook Discussion
  • 32. Agenda
    • Introduction:
      • Why: The Biosecurity Portal Project
      • How: The modeling approach
    • Framework for ontology creation
    • Application of framework :
      • Creation of the Biosecurity Ontology
    • Outlook:
      • Application scenario
    • Discussion
    Introduction Framework Application Outlook Discussion