1. II Jornadas sobre Ontologías y Web Semántica. WebSemántica'2007
Method 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. 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. 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. 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. Examples (spanish concept maps)
Medical Domain Ontology from the @LIS TechNET Project

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. 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. 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. 1st Phase.
Concept sense disambiguation
Senses of Arteria
Concept Map
concept
Domain

10. 2nd Phase.
Initial coding of OWL classes

11. 3rd Phase.
Identification of subclass relations

12. 3rd Phase.
Identification of subclass relations
hypernym relations in WordNet

13. 4th Phase.
Identification of instance relations

14. 5th Phase.
Identification of property relations

15. 5th Phase.
Identification of property relations

16. 5th Phase.
Identification of property relations

17. 5th Phase.
Identification of property relations

18. 5th Phase.
Identification of property relations

19. Implementation and Validation
 Java application
Input: XML (generated for Macosoft
-Concept Maps Editor)
Output: OWL
 Validated with Protégé and
WonderWeb OWL Ontology Validator

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. 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