Upload
vangie
View
26
Download
3
Embed Size (px)
DESCRIPTION
The Agricultural Ontology Service (AOS) Effort for Content Standardization in Agriculture Frehiwot Fisseha (UNFAO) [email protected]. Outline. FAO’s mandate in agricultural information management Problems we want to solve The current situation Proposed solution - PowerPoint PPT Presentation
Citation preview
Slide 1
09-05-2002
The Agricultural Ontology Service(AOS)
Effort for Content Standardization in Agriculture
Frehiwot Fisseha (UNFAO)
Slide 2
09-05-2002
Outline
• FAO’s mandate in agricultural information management
• Problems we want to solve
• The current situation
• Proposed solution
• The Agricultural Ontology Service (AOS)
• AOS prototype (The Fishery Ontology Service)
Slide 3
09-05-2002
FAO’s mandate
• FAO’s main goal is to reduce the number of hungry people by 50% within the year 2015.
• WAICENT (World Agricultural Information Center) is FAO’s approach to fight hunger with information.
• FAO produces a huge amount of data/information in agriculture and related disciplines.
• It is also within FAO’s mandate to make available agriculture related information from other information providers.
• FAO collaborates in information networks which are dedicated to the dissemination of agricultural domain.
Slide 4
09-05-2002
Problems we want to solve
“The Information Organization” problem faced by Information Managers
At present most information management tasks are performed manually.
... consider the cataloging and indexing task….
Manual cataloging and indexing are labor-intensive processes, requiring special training.
Tools for automating or semi-automating these processes are much in demand.
Slide 5
09-05-2002
Problems we want to solve
Both parameters are ranking low today!
Recall: Number of Relevant Documents in the Collection
Number of Relevant Documents Identified
Precision: Number of Relevant Documents Identified
Total Number of Documents Identified
“The Information Retrieval” problem faced by Information Users
Slide 6
09-05-2002
Problems we want to solve
• Topic Trees from categorization schemes and thesauri are rigid and not very expressive
• Machine produced clusters are “flexible”, but imprecise and at times out of context
Slide 7
09-05-2002
Knowledge Organizations Systems: Metadata Schema
• The subject categorization schemes are not adequately developed to be of use for semantic description for web resources
• The metadata schemas are closely attached to traditional description of bibliographical records
• The Dublin Core Metadata Initiative (DCMI) is a step forward to define core metadata to describe information objects
• Effort is underway to develop Agricultural metadata standards
Slide 8
09-05-2002
Knowledge Organization Systems: Vocabularies
AGROVOC
NAL Thesaurus
CABI Thesaurus
Dedicated KOSs
Non-dedicated KOSs
e.g., ASFA thesaurus
e.g., the Multilingual Forestry Thesaurus
e.g., the Sustainable Development
website classification
e.g., biological taxonomies such as NCBI and ITIS
GEMET
Other thematic thesauri
Existing Thesauri and Knowledge Organization Systems (KOSs)
Common concepts are not declared
No or very limited interoperability
Insufficient subject + language coverage
Severe maintenance problems
Very limited machine readability
Only very simple encoding of semantic relations
Slide 9
09-05-2002
Some observations
• No cross navigation between applications
• Full text search engines based on statistical text analysis are imprecise
Systems based only on “machine intelligence” do not show too promising results
• Web crawlers and harvesters do good jobs only on already structured information sources.
Recognition of meaning (semantic analysis) by machines is only possible by using using structured meta-information and formal knowledge description Agreed metadata schemas Controlled vocabularies, Taxonomies
Slide 10
09-05-2002
The solution we propose- Domain Ontology
An ontology is a formal knowledge organization system
A formal description of the application knowledge
It contains concepts and their definitions
Relations between concepts
Possibility for machine processing
Slide 11
09-05-2002
What benefits do we expect from Ontology?
– Semantic Organization of websites Knowledge maps Guided discovery of knowledge Easy retrievability of information without using complicated Boolean logic
– Text processing by machines Text Mining on the Web (meaning-oriented access) Automatic indexing and text annotation tools Full text search engines that create meaningful classification (FAO-
Schwartz not related to FAO) (semantic clustering)
– Intelligent search of the Web Building dynamical catalogues from machine readable meta data Cross Domain Search
– Natural Language processing Better machine translation Queries using natural language
Slide 12
09-05-2002
Guided Browse and Search Facilities
Records found: 5
1. xxxxxxxxxxx
2. xxxxxxxxxxx
3. xxxxxxxxxxx
4. xxxxxxxxxxx
5. xxxxxxxxxxx
BiotopesCropping systems using forestsEconomics of forest productionForestry equipmentSoil science
You may also be interested in...
What would you like to view?
Forest rights issuesParasites of forestsPesticides used in forestsTypes of forest productsUses of forest products
Geographic area
You can further limit by:
x
Africa
Web pageType of resource
Slide 13
09-05-2002
Context Sensitive Knowledge Access
Conservation agriculture
Farmers like it because it gives them a means of conserving, improving and making more efficient use of their natural resources
About camels and llamas
Descendants of the same rabbit-sized mammal, they have become two of humanity's most versatile domestic animals
Agribusiness and small farmers
Well managed contract farming contributes to both increased income for producers and higher profits for investors
Toward biosecurity
Biological and environmental risks associated with food and agriculture have intensified with economic globalization
Urban food marketing
In the “century of cities”, a major challenge will be providing adequate quantities of nutritional and affordable food for urban inhabitants
Crop science and ethics
In order to continue their contribution to human development, crop scientists must regain credibility
Use your right mouse button to learn more about an italicized word on the page.
Biosecurity:management of all biological and environmental risks associated with food and agriculture, including forestry and fisheries
See also:BiosafetyFood SafetyRisk Management
Or are you interested in...:Food SecurityBiological Diversity
Agricultural Web Page
Slide 14
09-05-2002
The Collaborative Approach We Want to Adopt
• Only agreed semantic standards guarantee knowledge discovery between different applications.
• Developing Knowledge Organization Systems is resource intensive and requires stakeholder’s agreement and participation.
• Hence, FAO started initiatives to bring interested partners together The AGStandards initiative was launched in October, 2000 to agree on
agricultural metadata standards The Agricultural Ontology Service (AOS) concept paper was publicized in
July 2001.
Slide 15
09-05-2002
What does Agricultural Ontology Service mean?
The Agricultural Ontology Service is an approach to organize knowledge organization systems that is
International The Internet must become multilingual
MultidisciplinaryThe field of agriculture is broad and multidisciplinary.
CooperativeStakeholders can contribute different expert knowledge
Distributed No central ownership
CoordinatedCoordination must ensure reusability and standardization
Slide 16
09-05-2002
AOS: Iterative Knowledge Registration
KOS uses components to build
an application
Discussions and choices for amendments to
components
Components: terms, definitions,
relationshipsUsers search and browse
application using components
User feedback
Agricultural Ontology Service (AOS)
Federated storage and description facility
Components: terms, definitions,
relationships
Slide 17
09-05-2002
Activities to date
• The first AOS workshop took place in Rome, November 2001– A launch group was established with participation of
– Content providers (FAO, CABI)
– Solution providers in the Agricultural Area (ATO -Wageningen, University of Florida)
– Ontology development Groups (AIFB Karlsruhe, CNR Italy) – Ontology experts
The second AOS workshop (January 2002 in Oxford)
– Decision to develop prototypes as proof of concept. – The Fishery Ontology Service (FOS) is one of the prototypes
The third AOS workshop took (May 2002 Florida)– Decision to setup the AOS consortium
Slide 18
09-05-2002
AOS – a “business model”
• A consortium of Information Providers
• A clearinghouse for semantic standards in agriculture and related discipline.
• One stop access to agreed standards (Ontologies, Metadata schemas, Vocabularies…).
• Participation as a consortium in semantic web activities (Ontoweb).
• Organization of seminars and workshops to further develop and
promote the use of semantic standards.
Slide 19
09-05-2002
AOS Prototype-
The Fishery Ontology Service (FOS)
Goal: to integrate the multilingual fishery and aquatic resources terminology
– the oneFish Community Directory, – ASFA,– FIGIS, – AGROVOC
Objective:– to have a better tool for document indexing and information retrieval, – to promote interaction and knowledge sharing within the fishery
community