Successfully reported this slideshow.
II Jornadas sobre Ontologías y Web Semántica. WebSemántica2007Method for ontology generation from concept maps in shallow ...
Introduction   The development and use of ontologies is    increasing today   The design and creation of ontologies, the...
Method proposed   Integration between an informal, flexible and    graphic model of knowledge (*Concept Map)    and OWL o...
Concept Map   Defined by Novak (70’s) within the pedagogical    sciences as graphical tools for organize and    represent...
Examples (spanish concept maps) Medical Domain   Ontology from the @LIS TechNET Project
Concept maps & OWL ontologies   It is an ontological and conceptual knowledge    representation   It is a sort of semant...
Formal Transformation   To increase the formalization levels of    the link-words in the concept map   To analyze the co...
1st Phase.Concept sense disambiguation   Identification of the Concept Map    Domain   Concept Sense Disambiguation for ...
1st Phase.Concept sense disambiguation             Senses of Arteria                                 Concept Map          ...
2nd Phase.Initial coding of OWL classes
3rd Phase.Identification of subclass relations
3rd Phase.Identification of subclass relations                      hypernym relations in   WordNet
4th Phase.Identification of instance relations
5th Phase.Identification of property relations
5th Phase.Identification of property relations
5th Phase.Identification of property relations
5th Phase.Identification of property relations
5th Phase.Identification of property relations
Implementation and Validation Java applicationInput: XML (generated for Macosoft  -Concept Maps Editor)Output: OWL   Val...
Conclusions   It has been shown that a tight relationship exists    between conceptual maps and ontologies   The interpr...
Future Work   identifications of more OWL specifications    inside the concept maps as:    TransitiveProperty and Symmetr...
Upcoming SlideShare
Loading in …5
×

Method for ontology generation from concept maps in shallow domains

1,182 views

Published on

Published in: Education
  • Be the first to comment

Method for ontology generation from concept maps in shallow domains

  1. 1. II Jornadas sobre Ontologías y Web Semántica. WebSemántica2007Method for ontology generation from concept maps in shallow domains Alfredo Simón1 Luigi Ceccaroni2 Alejandro Rosete1 1 Technical Institute “José Antonio Echeverría” (Cuba) 2 Technical University of Catalonia, Software department (Spain) asimon@ceis.cujae.edu.cu
  2. 2. Introduction The development and use of ontologies is increasing today The design and creation of ontologies, the tools available and the specification languages are still complex (*environment of human collaboration) These suggests the use of a form of representation that can be used naturally by humans and integrated with ontologies
  3. 3. Method proposed Integration between an informal, flexible and graphic model of knowledge (*Concept Map) and OWL ontologies It based on a concept sense-disambiguation procedure and WordNet It applied to concept maps of shallow domain with labels in the Spanish language Oriented to obtain OWL-Lite and OWL-DL
  4. 4. Concept Map Defined by Novak (70’s) within the pedagogical sciences as graphical tools for organize and represent descriptive knowledge Kind of semantic network but not formal and more flexible Include concepts and relationship between concepts Propositions (concept, link-word, concept) are the smallest semantic structure with proper sense Oriented to be used and interpreted by humans Knowledge is expressed in natural language
  5. 5. Examples (spanish concept maps) Medical Domain Ontology from the @LIS TechNET Project
  6. 6. Concept maps & OWL ontologies It is an ontological and conceptual knowledge representation It is a sort of semantic network. Therefore similar to Frame Systems but it isn’t enough propositions and triples (subject, predicate, object) of RDF have similar structures structural correspondence: concept with class/subclass links and link-word with property propositions with restriction and other OWL specifications
  7. 7. Formal Transformation To increase the formalization levels of the link-words in the concept map To analyze the concept map as a structured text: Identify the correct sense of the concepts (synset in WordNet) Identify the semantic of the relation between concepts using WordNet (hypernym-hyponym, meronym-holonym) Five Phases
  8. 8. 1st Phase.Concept sense disambiguation Identification of the Concept Map Domain Concept Sense Disambiguation for Domain Concept Sense Disambiguation for Context Using Spanish WordNet Lexical Database
  9. 9. 1st Phase.Concept sense disambiguation Senses of Arteria Concept Map concept Domain
  10. 10. 2nd Phase.Initial coding of OWL classes
  11. 11. 3rd Phase.Identification of subclass relations
  12. 12. 3rd Phase.Identification of subclass relations hypernym relations in WordNet
  13. 13. 4th Phase.Identification of instance relations
  14. 14. 5th Phase.Identification of property relations
  15. 15. 5th Phase.Identification of property relations
  16. 16. 5th Phase.Identification of property relations
  17. 17. 5th Phase.Identification of property relations
  18. 18. 5th Phase.Identification of property relations
  19. 19. Implementation and Validation Java applicationInput: XML (generated for Macosoft -Concept Maps Editor)Output: OWL Validated with Protégé and WonderWeb OWL Ontology Validator
  20. 20. Conclusions It has been shown that a tight relationship exists between conceptual maps and ontologies The interpretation of conceptual maps as structured text allows the semantic inference needed for their coding in OWL, without losing flexibility The defined procedures generate OWL ontologies from conceptual maps The proposed integration creates the bases for generalization to other domains and for the collaborative development of ontologies
  21. 21. Future Work identifications of more OWL specifications inside the concept maps as: TransitiveProperty and SymmetricProperty, property value (hasValue), intersection of class (intersectionOf) and equivalent class reuse of public ontologies and concept maps repositories

×