1. 1 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt CS 9010: Knowledge-Based Systems Ontologies and OWL Paula Matuszek Spring, 2011

2. 2 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt What Is An Ontology An ontology is an explicit description of a domain: –concepts –properties and attributes of concepts –constraints on properties and attributes –Individuals (often, but not always) An ontology defines –a common vocabulary –a shared understanding

3. 3 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Ontology Examples Taxonomies on the Web –Google Directory, Google RecipesGoogle DirectoryGoogle Recipes Catalogs for on-line shopping –Amazon.com product catalogAmazon.com product catalog Domain-specific standard terminology –Unified Medical Language System (UMLS) and MeSH Broad general ontologies –CycCyc

4. 4 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt

5. 5 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt

6. 6 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt

7. 7 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Cyc Ontology

8. 8 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Why Develop an Ontology? To share common understanding of the structure of information –among people –among software agents To enable reuse of domain knowledge –to avoid “re-inventing the wheel” –to introduce standards to allow interoperability

9. 9 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt More Reasons To make domain assumptions explicit –easier to change domain assumptions (consider a genetics knowledge base) –easier to understand and update legacy data To separate domain knowledge from the operational knowledge –re-use domain and operational knowledge separately (e.g., configuration based on constraints)

10. 10 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Which wine should I serve with seafood today? What wines should I buy next Monday for my reception in Villanova, PA? Is there a market for the products of another small winery in this area? What online source is the best for wines for my party in Texas next fall? Consider Questions Like:

11. 11 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt What Do We Need to Know?

12. 12 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt French wines and wine regions California wines and wine regions Which wine should I serve with seafood today? A shared ONTOLOGYof wine and food A shared ONTOLOGYof wine and food

13. 13 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Wines and Wineries

14. 14 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt An Ontology Is Often Just the Beginning Ontologies Software agents Problem- solving methods Domain- independent applications Databases Declare structure Knowledge bases Provide domain description

15. 15 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt What does an Ontology Look Like? Can be any knowledge representation Typically a description logic or associative network of some kind. Internal RepresentationEnglish RepresentationFacts Reasoning Programs

16. 16 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Description Logics Modeling-based representations reflect the structure of the domain, and then reason based on the model. –Semantic Nets –Frames –Scripts Sometimes called associative networks

17. 17 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Basics of Description Logics All include –Concepts –Various kinds of links between concepts “has-part” or aggregation “is-a” or specialization More specialized depending on domain Typically also include –Inheritance –Some kind of procedural attachment or restrictions or constraints

18. 18 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Ontology-Development Process General approach: determine scope consider reuse enumerate terms define classes define properties define constraints create instances Usually a highly iterative process. (Sound familiar?)

19. 19 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Preliminaries - Tools All screenshots in this tutorial are from Protégé, which: –is a graphical ontology-development tool –supports a rich knowledge model –is open-source and freely available (http://protege.stanford.edu) Some other available tools: –Ontolingua and Chimaera –OntoEdit –OilEd –OpenCyc

20. 20 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Determine Domain and Scope What is the domain that the ontology will cover? For what we are going to use the ontology? For what types of questions the information in the ontology should provide answers (competency questions)? determine scope consider reuse enumerate terms define classes define properties define constraints create instances

21. 21 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Competency Questions Which wine characteristics should I consider when choosing a wine? Is Bordeaux a red or white wine? Does Cabernet Sauvignon go well with seafood? What is the best choice of wine for grilled meat? Which characteristics of a wine affect its appropriateness for a dish? Does a flavor or body of a specific wine change with vintage year? What were good vintages for Napa Zinfandel?

22. 22 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Consider Reuse Why reuse other ontologies? –to save the effort –to interact with the tools that use other ontologies –to use ontologies that have been validated through use in applications determine scope consider reuse enumerate terms define classes define properties define constraints create instances

23. 23 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt What to Reuse? Ontology libraries –Protégé ontology library (protege.cim3.net/cgi- bin/wiki.pl?ProtegeOntologiesLibrary)protege.cim3.net/cgi- bin/wiki.pl?ProtegeOntologiesLibrary –Biomedical ontologies (bioontology.org) –Many others: try Googling for your topic –http://www.dmoz.org/http://www.dmoz.org Upper ontologies –IEEE Standard Upper Ontology ( suo.ieee.org) –Cyc (www.cyc.com)

24. 24 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Enumerate Important Terms What are the terms we need to talk about? What are the properties of these terms? What do we want to say about the terms? consider reuse determine scope enumerate terms define classes define properties define constraints create instances

25. 25 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Enumerating Terms - The Wine Ontology wine, grape, winery, location, wine color, wine body, wine flavor, sugar content white wine, red wine, Bordeaux wine food, seafood, fish, meat, vegetables, cheese

26. 26 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Define Classes and the Class Hierarchy A class is a concept in the domain –a class of wines –a class of wineries –a class of red wines A class is a collection of elements with similar properties Instances of classes –a glass of California wine you’ll have for lunch consider reuse determine scope define classes define properties define constraints create instances enumerate terms

27. 27 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Class Inheritance Classes usually constitute a taxonomic hierarchy (a subclass-superclass hierarchy) A class hierarchy is usually an IS-A hierarchy: an instance of a subclass is an instance of a superclass If you think of a class as a set of elements, a subclass is a subset

28. 28 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Class Inheritance - Example Apple is a subclass of Fruit Every apple is a fruit Red wines is a subclass of Wine Every red wine is a wine Chianti wine is a subclass of Red wine Every Chianti wine is a red wine

29. 29 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Levels in the Hierarchy Middle level Top level Bottom level

30. 30 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Modes of Development top-down – define the most general concepts first and then specialize them bottom-up – define the most specific concepts and then organize them in more general classes combination – define the more salient concepts first and then generalize and specialize them

31. 31 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Documentation Classes (and properties) usually have documentation –Describing the class in natural language –Listing domain assumptions relevant to the class definition –Listing synonyms Documenting classes and properties is as important as documenting computer code!

32. 32 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Define Properties of Classes – Properties Properties in a class definition describe attributes of instances of the class and relations to other instances Each wine will have color, sugar content, producer, etc. consider reuse determine scope define constraints create instances enumerate terms define classes define properties

33. 33 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Properties (Properties) Types of properties –“intrinsic” properties: flavor and color of wine –“extrinsic” properties: name and price of wine –parts: ingredients in a dish –relations to other objects: producer of wine (winery) Simple and complex properties –simple properties (attributes): contain primitive values (strings, numbers) –complex properties: contain (or point to) other objects (e.g., a winery instance)

34. 34 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Properties for the Class Wine (in Protégé-2000)

35. 35 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Property and Class Inheritance A subclass inherits all the properties from the superclass If a wine has a name and flavor, a red wine also has a name and flavor If a class has multiple superclasses, it inherits properties from all of them Port is both a dessert wine and a red wine. It inherits “sugar content: high” from the former and “color:red” from the latter

36. 36 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Property Constraints Property constraints (restrictions) describe or limit the set of possible values for a property The name of a wine is a string The wine producer is an instance of Winery A winery has exactly one location consider reuse determine scope create instances enumerate terms define classes define constraints define properties

37. 37 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Restrictions for Properties at the Wine Class

38. 38 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Common Restrictions Property cardinality – the number of values a property has Property value type – the type of values a property has Minimum and maximum value – a range of values for a numeric property Default value – the value a property has unless explicitly specified otherwise

39. 39 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Common Restrictions: Property Cardinality Cardinality –Cardinality N means that the property must have N values Minimum cardinality –Minimum cardinality 1 means that the property must have a value (required) –Minimum cardinality 0 means that the property value is optional Maximum cardinality –Maximum cardinality 1 means that the property can have at most one value (single-valued property) –Maximum cardinality greater than 1 means that the property can have more than one value (multiple-valued property)

40. 40 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Common Restrictions: Value Type String: a string of characters (“Château Lafite”) Number: an integer or a float (15, 4.5) Boolean: a true/false flag Enumerated type: a list of allowed values (high, medium, low) Complex type: an instance of another class –Specify the class to which the instances belong The Wine class is the value type for the property “produces” at the Winery class

41. 41 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Domain and Range of Property Domain of a property – the class (or classes) that have the property –More precisely: class (or classes) instances of which can have the property Range of a property – the class (or classes) to which property values belong

42. 42 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Restrictions and Class Inheritance A subclass inherits all the properties from the superclass A subclass can override the restrictions to “narrow” the list of allowed values –Make the cardinality range smaller –Replace a class in the range with a subclass Wine French wine Winery French winery is-a producer

43. 43 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Create Instances Create an instance of a class –The class becomes a direct type of the instance –Any superclass of the direct type is a type of the instance Assign property values for the instance frame –Property values should conform to the facet constraints –Knowledge-acquisition tools often check that consider reuse determine scope create instances enumerate terms define classes define properties define constraints

44. 44 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Creating an Instance: Example

45. 45 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Defining Classes and a Class Hierarchy The things to remember: –There is no single correct class hierarchy –But there are some guidelines The question to ask: “Is each instance of the subclass an instance of its superclass?”

46. 46 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Disjoint Classes Classes are disjoint if they cannot have common instances Disjoint classes cannot have any common subclasses either Red wine, White wine, Rosé wine are disjoint Dessert wine and Red wine are not disjoint Wine Red wine Rosé wine White wine Dessert wine Port

47. 47 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Classes and Their Names Classes represent concepts in the domain, not their names The class name can change, but it will still refer to the same concept Synonym names for the same concept are not different classes –Many systems allow listing synonyms as part of the class definition

48. 48 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Back to the Properties: Domain and Range When defining a domain or range for a property, find the most general class or classes Consider the flavor property –Domain: Red wine, White wine, Rosé wine –Domain: Wine Consider the produces property for a Winery: –Range: Red wine, White wine, Rosé wine –Range: Wine

49. 49 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Back to the Properties: Domain and Range When defining a domain or range for a property, find the most general class or classes Consider the flavor property –Domain: Red wine, White wine, Rosé wine –Domain: Wine Consider the produces property for a Winery: –Range: Red wine, White wine, Rosé wine –Range: Wine propertyclassallowed values DOMAINRANGE

50. 50 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Inverse Properties Maker and Producer are inverse properties

51. 51 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Inverse Properties (II) Inverse properties contain redundant information, but –Allow acquisition of the information in either direction –Enable additional verification –Allow presentation of information in both directions The actual implementation differs from system to system –Are both values stored? –When are the inverse values filled in? –What happens if we change the link to an inverse property?

52. 52 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Limiting the Scope An ontology should not contain all the possible information about the domain –No need to specialize or generalize more than the application requires –No need to include all possible properties of a class Only the most salient properties Only the properties that the applications require

53. 53 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Limiting the Scope (II) Ontology of wine, food, and their pairings probably will not include –Bottle size –Label color –My favorite food and wine An ontology of biological experiments will contain –Biological organism –Experimenter Is the class Experimenter a subclass of Biological organism?

54. 54 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Ontology Languages RDF and RDFS DAML+OIL OWL Cyc-L Others OWL has a special status within the semantic web community

55. 55 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt OWL Representation An OWL file is a text file –XML –Uses RDFS –Plus OWL-specific extensions If you are using a tool like Protege to create your ontology you don’t need to know the underlying representation If you’re going to do something with it, you do.

56. 56 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt OWL Example This ontology Becomes this text file: wine.txtwine.txt 56

57. 57 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt OWL: Classes And a Class Hierarchy Classes –Each class is an instance of owl:Class Class hierarchy –Defined by rdfs:subClassOf More ways to specify organization of classes –Disjointness (owl:disjointWith) –Equivalence (owl:EquivalentClass) Predefined: owl:Thing, owl:Nothing

58. 58 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt More Ways To Define a Class in OWL Union of classes: owl:unionOf A class Person is a union of classes Male and Female Intersection of classes: owl:intersectionOf A class Red Wine is an intersection of Wine and Red Thing Complement of a class: owl:complementOf Carnivores are all the animals that are not herbivores Enumeration of elements: owl:oneOf A class Wine Color contains the following instances: red, white, rosé Restriction on properties: owl:Restriction A class Red Thing is a collection of things with color: Red

59. 59 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Properties in OWL Two kinds of property –owl:ObjectProperty. Object properties relate objects to other objects. Example: Goes-well- with. –owl:datatypeProperty. Datatype properties relate objects to datatype values. Example: Has-cost. Properties can be equivalent –owl:equivalentProperty. Example: bottled-by and produced-by

60. 60 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Some Special Properties in OWL owl:TransitiveProperty –Is more expensive than owl:SymmetricProperty –Comes from vinyard owl:FunctionalProperty –Has UPC code owl:InverseFunctionalProperty –Is UPC code of

61. 61 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Research Issues in Ontology Creation Content generation Analysis and evaluation Maintenance Ontology languages Tool development

62. 62 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Content: Top-Level Ontologies What does “top-level” mean? –Objects: tangible, intangible –Processes, events, actors, roles –Agents, organizations –Spaces, boundaries, location –Time IEEE Standard Upper Ontology effort –Goal: Design a single upper-level ontology –Process: Merge upper-level of existing ontologies

63. 63 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Content: Knowledge Acquisition Knowledge acquisition is a bottleneck Sharing and reuse alleviate the problem But we need automated knowledge acquisition techniques –Linguistic techniques: ontology acquisition from text –Machine-learning: generate ontologies from structured documents (e.g., XML documents) –Exploiting the Web structure: generate ontologies by crawling structured Web sites –Knowledge-acquisition templates: experts specify only part of the knowledge required

64. 64 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Analysis Analysis: semantic consistency –Violation of property constraints –Cycles in the class hierarchy –Terms which are used but not defined –Interval restrictions that produce empty intervals (min > max) Analysis: style –Classes with a single subclass –Classes and properties with no definitions –Properties with no constraints (value type, cardinality)

65. 65 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Evaluation One of the hardest problems in ontology design Ontology design is subjective What does it mean for an ontology to be correct (objectively)? The best test is the application for which the ontology was designed

66. 66 CSC 9010 Spring, 2011. Paula Matuszek Slides modified from Natasha Noy, protege.stanford.edu/amia2003/AMIA2003Tutorial.ppt Ontology Languages What is the “right” level of expressiveness? What is the “right” semantics? When does the language make “too many” assumptions?

67. 67 CSC 9010 Spring, 2006. Paula Matuszek. Paula.A.Matuszek@gsk.com Problems with Hand-Crafting Requires both skill in building ontologies and knowledge of the domain Tremendously time consuming, even with tools like Protégé. Easy to end up with errors –Inheritance –Defaults –Instances Hard to keep up to date.

68. 68 CSC 9010 Spring, 2006. Paula Matuszek. Paula.A.Matuszek@gsk.com What Can Help? Some Technologies NLP tools –Term extraction Document summarization and topic tree creation (www.megaputer.com)www.megaputer.com Entity and relationship extraction to get instances Machine Learning –Association-rule-learning algorithms –Bayesian Classifiers –Rule induction –Clustering Note: these are all classification tools of some kind

69. 69 CSC 9010 Spring, 2006. Paula Matuszek. Paula.A.Matuszek@gsk.com What Can Help? Semi-automated Ontology Building Extract from existing data on the web with Google-type search –KnowItAll: Etzioni et al –Cyc: Matuszek et al KCVC: knowledge contribution from volunteer contributors –FACTory –ESPGame

70. 70 CSC 9010 Spring, 2006. Paula Matuszek. Paula.A.Matuszek@gsk.com Knowledge Management Ontologies represented in OWL/RDF/XML have many of the same issues as any software development project –Change Management and tracking –Permissions and ownership –Components and reuse