Transcript

Ontology Matching Basics - PL, CS 652 1

Ontology Matching Basics

Ontology Matchingby Jerome Euzenat and Pavel Shvaiko

Parts I and II

11/6/2012

Ontology Matching Basics - PL, CS 652 2

1 - Applications

1.1 Ontology engineering1.2 Information integration1.3 Peer-to-peer information sharing1.4 Web service composition1.5 Autonomous communication systems1.6 Navigation and query answering on the web

11/6/2012

Ontology Matching Basics - PL, CS 652 311/6/2012

Ontology Matching Basics - PL, CS 652 411/6/2012

Ontology Matching Basics - PL, CS 652 511/6/2012

Ontology Matching Basics - PL, CS 652 611/6/2012

Ontology Matching Basics - PL, CS 652 711/6/2012

Ontology Matching Basics - PL, CS 652 8

2 – The matching problem

2.1 Vocabularies, schemas and ontologies2.2 Ontology language2.3 Types of heterogeneity2.4 Terminology2.5 The ontology matching problem

11/6/2012

Ontology Matching Basics - PL, CS 652 9

2.1 Vocabularies, schemas and ontologies

• Tags and folksonomies• Directories• Relational database schemas• XML schemas• Conceptual models• Ontologies – model-theoretic semantics,

“ontologies are logic theories”

11/6/2012

Ontology Matching Basics - PL, CS 652 10

2.2 Ontology language (OWL)

• Entities:– Classes– Individuals– Relations– Datatypes– Data values

• Entity relations– Specialization– Exclusion– Instantiation

11/6/2012

Ontology Matching Basics - PL, CS 652 1111/6/2012

Ontology Matching Basics - PL, CS 652 1211/6/2012

Ontology Matching Basics - PL, CS 652 13

2.4 - Terminology

11/6/2012

Ontology Matching Basics - PL, CS 652 14

2.5 – The ontology mapping problem

11/6/2012

Ontology Matching Basics - PL, CS 652 1511/6/2012

Ontology Matching Basics - PL, CS 652 1611/6/2012

Ontology Matching Basics - PL, CS 652 1711/6/2012

Ontology Matching Basics - PL, CS 652 18

2.3 – Types of heterogeneity

• Syntactic heterogeneity– Not expressed in the same ontology language

• Terminological heterogeneity– Variation in names for the same entity

• Conceptual heterogeneity– Differences in coverage, granularity, or perspective

• Semiotic (pragmatic) heterogeneity– How entities are interpreted by people

11/6/2012

Ontology Matching Basics - PL, CS 652 19

3 – Classification of ontology matching techniques

3.1 Matching dimensions- Input dimensions- Process dimensions- Output dimensions

3.2 Classification of matching approaches- Exhaustivity- Disjointedness- Homogeneity- Saturation

3.3 Other classifications- Horizontal: data, ontology, and context layers- Vertical: syntactic, pragmatic, conceptual

11/6/2012

Ontology Matching Basics - PL, CS 652 2011/6/2012

Ontology Matching Basics - PL, CS 652 21

Element-level techniques

• String-based techniques• Language-based techniques• Constraint-based techniques• Linguistic resources• Alignment reuse• Upper level and domain specific formal

ontologies

11/6/2012

Ontology Matching Basics - PL, CS 652 22

Structure-level techniques

• Graph-based techniques• Taxonomy-based techniques• Repository of structures• Model-based techniques• Data analysis and statistical techniques

11/6/2012

Ontology Matching Basics - PL, CS 652 23

4 – Basic techniques

4.1 Similarity, distances and other measures4.2 Name-based techniques4.3 Structure-based techniques4.4 Extensional techniques4.5 Semantic-based techniques

11/6/2012

Ontology Matching Basics - PL, CS 652 24

4.2 – Name-based techniques

• Problem: synonyms and homonyms (polysemy)• String-based methods– Normalization– String equality– Substring test– Edit, token-based, and path distances

• Language-based methods– Intrinsic methods– Extrinsic methods

11/6/2012

Ontology Matching Basics - PL, CS 652 2511/6/2012

Ontology Matching Basics - PL, CS 652 26

4.3 – Structure-based techniques

• Internal structure– Property comparison– Datatype comparison– Domain comparison– Comparing multiplicities

and properties– Other features

• Relational structure– Maximum common

directed subgraph problem

– Taxonomic structure– Mereologic structure– Relation similarities

11/6/2012

Ontology Matching Basics - PL, CS 652 2711/6/2012

Ontology Matching Basics - PL, CS 652 2811/6/2012

Ontology Matching Basics - PL, CS 652 29

4.4 – Extensional techniques

• Common extension comparison– Hamming distance– Jaccard similarity– Formal concept analysis – intent and extent

• Instance identification techniques• Disjoint extension comparison– Statistical approach– Similarity-based extension comparison– Matching-based comparison

11/6/2012

Ontology Matching Basics - PL, CS 652 30

4.5 – Semantic-based techniques

• Model-theoretic, deductive methods• Act to amplify seeding alignments• Techniques based on external ontologies• Deductive techniques– Propositional satisfiability– Modal satisfiability– Description logic techniques

11/6/2012

Ontology Matching Basics - PL, CS 652 31

5 – Matching strategies

5.1 Matcher composition5.2 Similarity aggregation5.3 Global similarity computation5.4 Learning methods5.5 Probabilistic methods5.6 User involvement and dynamic composition5.7 Alignment extraction

11/6/2012

Ontology Matching Basics - PL, CS 652 3211/6/2012

Ontology Matching Basics - PL, CS 652 3311/6/2012

Ontology Matching Basics - PL, CS 652 3411/6/2012

Ontology Matching Basics - PL, CS 652 3511/6/2012

Ontology Matching Basics - PL, CS 652 36

5.4 – Learning methods

• Bayes learning• WHIRL learner• Neural networks• Decision trees• Stacked generalization

11/6/2012

Ontology Matching Basics - PL, CS 652 3711/6/2012

Ontology Matching Basics - PL, CS 652 38

5.5 Probabilistic methods

• Bayesian networks

11/6/2012

Ontology Matching Basics - PL, CS 652 39

5.6 – User involvement and dynamic composition

• Providing input– Ontologies, parameters, initial alignment

• Manual matcher composition– Assemble from libraries– Examine results and iterate– Apply to application

• Relevance feedback

11/6/2012

Ontology Matching Basics - PL, CS 652 40

5.7 – Alignment extraction

• Select on similarity, extract, and filter

• Thresholds• Strengthening and weakening• Optimizing the result

11/6/2012

Ontology Matching Basics - PL, CS 652 4111/6/2012

Fig. 5.14 displays a fictitious example involving several of the methods. It (i)runs several basic matchers in parallel, (ii) aggregates their results, (iii) selects somecorrespondences on the basis of their (dis)similarity, (iv) extracts an alignment, (v) uses a semantic algorithm to amplify the selected alignment, and (vi) reiterate thisprocess if necessary.


Recommended