OntologyBased Integration of Information A Survey of Existing Approaches

1
Ontology-Based Integration of Information A
Survey of Existing Approaches

• H.Wache, T.Vogele, U.Visser, H.Stuckenschmidt,
  G.Schuster, H.Neumann and S.Hubner
• University of Bremen

2
Motivation

• Vast information is available on the WWW
• Growing need for
• Finding relevant information (Information
  Extraction)
• Creating new knowledge out of the available
  information (Web Content Mining)
• Personalization of the web
• Learning about customers or individual users (Web
  Usage Mining)

3
Issues

• Information is widely distributed and
  heterogeneous
• Schema discovery
• Wrapping
• Reorganizing data sources
• Coping with changes in sources

4
Issues (cont.)

• Structural (schematic) heterogeneity
• Data is stored in different structures across the
  information systems
• Semantic (data) heterogeneity
• Considers the content of an information and its
  intended meaning
• Causes
• Confounding conflicts
• Items that have the same meaning but differ in
  reality
• Scaling conflicts
• Different reference systems are used to measure a
  value (Eu, )
• Naming conflicts
• Naming schemes of similar items differ
  significantly

5
Solution - Ontologies

• Refers to shared understanding of a domain of
  interest which may be used as a unifying
  framework
• Embodies some sort of world view with respect to
  a given domain
• World view is conceived as
• Set of concepts (entities, attributes, processes)
• Definitions
• Inter-relationships
• This is referred to as conceptualization

6
Ontologies (cont.)

• consensual, shared and formal description of the
  concepts that are important in a given domain
• identifies classes of objects that are important
  in a domain and organizes these classes in a
  subclass hierarchy
• each class is characterized by properties shared
  by all elements in that class
• important relations between classes or between
  the elements of the classes are also part of an
  ontology

7
Ontology example
8
Objective

• Evaluate the use of ontologies in information
  integration systems
• SIMS, TSIMMIS, OBXERVER, CARNOT, Infosleuth,
  KRAFT, PICSEL, DWQ, Ontobroker, SHOE

9
Criteria for evaluating approaches

• Use of ontologies
• Purpose of using ontologies
• Architecture of ontologies used
• Ontology representation
• Kind of languages used to represent ontologies
• General structure of ontologies
• Use of mappings
• How information is mapped to ontologies
• Inter-ontology mapping
• Ontology engineering
• Support for development of ontolgies
• Support for evolution of ontologies
• Supporting tools

10
Outline

• 1) Motivation
• 2) Issues
• 3) Brief introduction to Ontology
• 4) Objective
• 5) Role of Ontologies
• 6) Ontology Representation
• 7) Ontology Mappings
• 8) Ontology Engineering

11
5. Role of Ontologies

• Content explication
• Ontologies are used for the explicit description
  of the information source
• Approaches
• Single ontology
• Multiple ontology
• Hybrid ontology
• Query model
• Verification (query containment)

12
5.1 Single Ontology Approach

• SIMS
• One global ontology
• Hierarchical terminological database
• Combination of several specialized ontolgies
• (for modularization)
• Can be used when all information sources to be
  integrated provide nearly the same view on a
  domain
• Minimal ontology commitment
• Susceptible to changes in the information sources

13
5.2 Multiple Ontologies

• OBSERVER
• Each information source is described by its own
  ontology (source ontology)
• No shared vocabulary
• No common and minimal ontology commitment is
  needed
• Simplifies integration and supports changes in
  sources
• Difficult to compare different source ontologies
• Inter-ontology mapping is needed

14
5.3 Hybrid Ontologies

• COIN
• Semantics of each source is described by its own
  ontology
• Built from a a global shared vocabulary
• Shared vocabulary contains basic terms of a
  domain
• New sources can easily be added
• Supports acquisition and evolution of ontologies
• Source ontologies are comparable because of
  shared vocabulary
• Existing ontologies can not easily be reused, but
  have to be redeveloped from scratch

15
5.4 Query Model

• Integrated global view
• Global query schema
• User formulates query in terms of the ontology
• System reformulates queries in terms of
  sub-queries for each source
• Structure of the query model should be more
  intuitive for the user

16
5.5 Verification

• mappings from a global schema to the local source
  schema
• Automatic verification
• Query containment
• Ontology concepts corresponding to the local
  sub-queries are contained in the ontology
  concepts related to the global query

17
6. Ontology Representations

• Kind of languages used and general structures
  that can be found
• Description Logics
• Frame-Based systems
• Formal Concept Analysis
• Object Languages
• Annotated Logics

18
6.1 Ontology Representations - cont

• Description Logics Formal semantics
  reasoning
• CLASSIC, GRAIL, LOOM, OIL
• Describe knowledge in terms of concepts and role
  restrictions
• Derive classification hierarchies automatically
  from concepts and role restrictions
• Decidability and completeness guarantee that
  reasoning algorithm always terminate with correct
  answers
• Reasoning tasks satisfiability, subsumption
  (is-a), instance checking, classification

19
6.2 Ontology Representations - cont

• Frame-based systems
• OKBC, Ontolingua, F-Logic
• Frame is a structure for representing a concept
  or situation
• Frames are composed of slots (attributes) for
  which fillers (values) have to be specified
• Properties and restrictions can be provided for
  fillers
• DLs are descendants of frame-based systems
• Classes (objects/concepts), roles
  (attributes/properties)

20
6.3 Ontology Representations cont.

• Formal concept analysis
• Based on the calculation of a common concept
  hierarchy for different information sources
• limited expressiveness
• Object Languages
• designed for specific needs
• used in geographic domain
• provides solution for integration of spatial and
  thematic information
• Annotated Logics
• used to resolve conflicts
• eg. KAMEL

21
7. Mappings Connecting to Information Sources

• Relate the ontologies to the actual content of an
  information source
• Approaches
• Structure resemblance
• Produce a one-to-one copy of the structure of
  the database and encode it in a language that
  makes automated reasoning possible
• Definition of terms
• Use ontology to define terms from the database
  or the database scheme

22
7.1 Mappings (cont.)

• Structure enrichment (most common)
• A logical model is built that resembles the
  structure of the information source and contains
  additional definitions and concepts
• Can be done using DLs
• Meta-annotation
• Add semantic information to an information
  source
• ontobroker, SHOE

23
7.2 Inter-Ontological Mapping

• Defined Mappings (KRAFT)
• special customized mediator agents
• Great flexibility
• Fails to ensure a preservation of semantics - no
  verification
• Lexical Relations (OBSERVER)
• Extend a common DL model by quantified
  inter-ontology relationships
• Synonym, hypernym, overlap, covering, disjoint
• Do not have formal semantics

24
7.2 Inter-Ontology Mapping (cont.)

• Top-level grounding (DWQ)
• Relate all ontolgies used to a single top-level
  ontology
• Inheriting concepts from a common top-level
  ontology
• Can resolve conflicts and ambiguities
• Semantic correspondences
• Rely on a common vocabulary
• Uses semantic labels in order to compute
  correspondences
• Subsumption reasoning can be used to establish
  relations between different terminolgies

25
8. Ontological Engineering

• Development methodology
• 1) Identify a purpose and scope
• 2) Building the ontology
• 1) Ontology capture knowledge acquistion
• 2) Ontology coding developing a structured
  concept model
• 3) Integrating existing ontologies
• 4) Evaluation verification and validation
• 5) Guidelines for each phase

26
8.1 Development Methodology (cont.)

• Infosleuth
• Semi-automatically constructs ontologies from
  textual databases
• Experts provide seed words to represent
  high-level concepts
• Processes the incoming documents extracting
  phrases that involve seed words
• Generates corresponding concept terms and then
  classifies them into ontologies
• Needs experts for evaluation process (Phase -3 )
• Does not mention integration of existing
  ontologies

27
8.1 Development Methodology (cont.)

• SIMS
• An independent model of each info source must be
  described for this system
• Domain model defined to describe objects and
  actions
• Includes a hierarchical terminological knowledge
  base
• Indications of all relationships between the
  nodes
• Scalability and maintenance issues addressed
• Graphical knowledge base builder can be used

28
8.2 Supporting Tools

• OntoEdit
• Enables inspecting, browsing, codifying and
  modifying ontologies
• Support ontology development and maintenance
• SHOEs knowledge annotator
• Commits each web page to one or more ontologies
• Can define categories, relations and other
  components in an ontology
• Provides integrity checks
• Expose to parse annotated web pages
• Parka - knowledge base

29
8.2 Supporting Tools (cont.)

• DWQ i.com
• Supporting tool for the conceptual design phase
• Uses extended entity relationship conceptual data
  model
• Enriches it with aggregations and inter-schema
  constraints
• Serves mainly for intelligent conceptual modeling

30
8.3 Ontology Evolution

• Support for adding and/or removing sources
• Must be robust to changes in the information
  source
• SHOE only system that supports ontology
  evolution using Expose

31
End
32
Development Methodology (cont.)

• KRAFT
• Shared Ontologies
• Ontology scoping
• Domain analysis
• Ontology fomralization
• Top level ontology
• Extracting Ontologies
• Bottom-up approach to extract an ontology from
  existing shared ontolgies
• Syntactic translation from the KRAFT exportable
  view of the resource into the KRAFT-schema
• Ontological upgrade semi-automatic translation
  plus knowledge-based enhancement local ontology
  adds knowledge and further relationships between
  the entities in the translated schema
• Lack evaluation of the ontologies