Ontological Distance Measure for Conceptual Maps
160 likes | 184 Vues
Explore semantic distances and methods to measure similarity between concepts through ontology, vectors calculus, and geometric methods. Learn about formal definitions, properties, and resulting visualizations.
Ontological Distance Measure for Conceptual Maps
E N D
Presentation Transcript
Application Context 1 Application Context 2 T O F F C R I D A I [Touch-Graph] [ToxNuc-e project] [Treemaps] [Kartoo] [MBox Project]
Ontological Distance Measures for Information Visualisation on Conceptual Maps Sylvie Ranwez Vincent Ranwez Jean Villerd Michel Crampes LGI2P Research Centre – EMA, Nîmes ISEM – Montpellier University
Overview • Semantic distances: state-of-the-Art • From ontology to semantic distance • Intuitive approach • Formal definition • Example • Distance properties • Resulting visualisation • Discussion and perspectives • Conclusion Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Complementarity of the two approaches Semantic distances: state-of-the-Art Estimating similarity between concepts • Methods based on the concept hierarchy • d(a, b): the length of the shortest path between a and b[Sowa] • sim(a, b): function of common subsumers[Resnik] Considers only one point of view on the concept Supposes homogeneity of branches’ semantic Does not respect distances properties • Methods based on vectors calculus • Vectors of terms to describe a document • Vectors of concepts to describe a given concept • Ensemblist methods (Dice or Jaccard) • Geometric methods (cosines), Euclidian measure, distributional, etc. Vectors are not always available Lack of precision due to the vectorisation (synonyms) Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Overview • Semantic distances: state-of-the-Art • From ontology to semantic distance • Intuitive approach • Formal definition • Example • Distance properties • Resulting visualisation • Discussion and perspectives • Conclusion Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
T [MeSH] Persons (44) Occupational Groups (12) … Administrative Personnel (4) Health Personnel (20) Dentists (1) … Veterinarians (0) Nurses (6) … Trustees (0) • Physician Executives (0) From ontology to semantic distance • Intuitive approach on the is-a relation • Two concepts are close if there is a concept that sumbsumes both of them and if this concept is slightly more general (encompasses few more concepts) (encompasses few more concepts) d(Veterinarians, Nurses) < d(Trustees, Nurses) d(Nurses, Health Personnel) < d(Veterinarians, Health Personnel) Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
T Persons (44) Occupational Groups (12) … Administrative Personnel (4) Health Personnel (20) Dentists (1) … Veterinarians (0) Nurses (6) … Nurses Administrators (0) • Physician Executives (0) Trustees (0) From ontology to semantic distance • Intuitive approach on the is-a relation However multiple inheritance (points of view) must be taken into account Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
T C0 C1 C2 C3 C4 a C5 C6 C7 b C8 C9 C10 C11 • desc( ancExc(a,b) ) desc(a) desc(b)- desc(a) desc(b) • dISA(a, b) = | desc( ancExc(a, b) ) desc(a) desc(b) - desc(a) desc(b) | From ontology to semantic distance • Definition • ancExc(a,b) • desc( ancExc(a,b) ) desc(a) desc(b) • desc( ancExc(a,b) ) • dISA(a, b) = 11 Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
… Persons (44) Occupational Groups (12) … Administrative Personnel (4) Health Personnel (20) Dentists (1) … Veterinarians (0) Nurses (6) … Physician Executives (0) Nurses Administrators (0) Trustees (0) From ontology to semantic distance • dISA(a, b) = | desc( ancExc(a, b) ) desc(a) desc(b) - desc(a) desc(b) | • Example dISA(Trust., Nur.) = | desc( ancExc(Trust., Nur.) desc(Nur.) desc(Trust.) - desc(Nur.) desc(Trust.) | dISA(Trust., Nur.) = | desc(Health P., Admin P.) {Nur., …, Nur. adm.} {Trust.} - | dISA(Trust., Nur.) = | {Health P., Dentists, …, Nur., Nur. adm., Admin P., …, Trust.}| = 59 dISA(Nur. adm., Phys. Exec.) = 8 dISA(Trust., Phys. Exec.) = 58 dISA(Nur., Phys. Exec.) = 13 Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
From ontology to semantic distance • dISA(a, b) = | desc( ancExc(a, b) ) desc(a) desc(b) - desc(a) desc(b) | • Respects the three properties of a distance • Positiveness : a, b dISA(a, b)0 and dISA(a, b) = 0 a = b • Symmetry : a, b dISA(a, b) = dISA(b, a) • Triangle inequality : a, b, c dISA(a, c) + dISA(c, b) dISA(a, b) • Extension • Intuitive distance in a tree-like hierarchy when a subsumes b dISA(a, b) = | desc(a) – desc(b) | Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Overview • Semantic distances: state-of-the-Art • From ontology to semantic distance • Intuitive approach • Formal definition • Example • Resulting visualisation • Discussion and perspectives • Conclusion Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
… Persons (44) Occupational Groups (12) … Health Personnel (20) Administrative Personnel (4) … Dentists (1) Veterinarians (0) Nurses (6) … Nurses Administrators (0) Trustees (0) Resulting visualisation dISA(Trust., Nur.) = 59 dISA(Nur. adm., Phys. Exec.) = 8 dISA(Trust., Phys. Exec.) = 58 dISA(Nur., Phys. Exec.) = 13 Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Nervous System Diseases Neurologic Manifestations Pathological Conditions, Signs and Symptoms Central Nervous System Diseases Brain Diseases Sign and Symptoms Headache Disorder Pain Headache Disorder, Primary … Headache Migraine = Migraine Disorder Migraine Disorder with Aura Migraine Disorder without Aura Resulting visualisation Example from the MeSH Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Discussion and perspectives • Towards a semantic distance • Combine the ISA distance with other distance measures taking into account other kinds of relations • Combine with approaches using vector calculus • Combine the ISA distance with the level of detail of the concepts • Validation and extension of the visualisation • Visualisation of ontologies by projection and identification of clusters • Use of traditional clustering methods (hierarchical clustering, K-means…) • Comparisons and validation of our approach Enforce the use in industrial context • Validation of existing ontologies • Support during the conception of new ontologies • Support while navigating or searching for information Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Conclusion • Proposition of a distance using ISA relations, that respects the distance properties • Positiveness • Symmetry • Triangle inequality • Projection of ontologies: a new way of visualising ontologies • Towards conceptual maps • Support in ontologies building and validating • Application • Ontology design • Navigation support • Information retrieval Ontological Distance Measure for Information Visualisation on Conceptual Maps - S. Ranwez
Ontological Distance Measures for Information Visualisation on Conceptual Maps Sylvie.Ranwez@ema.fr http://www.lgi2p.ema.fr/~ranwezs Vincent.Ranwez@isem.univ-montp2.fr http://ranwez.free.fr/ Jean.Villerd@ema.fr http://www.lgi2p.ema.fr/~villerd Michel.Crampes@ema.fr http://www.ema.fr/~mcrampes