MultimediaN Application Pilot E-Culture

1
MultimediaN Application Pilot E-Culture

• Presentation and Demonstration

2
Outline

• Introduction The Project
• Goals/ Example Use Cases
• Semantic Web and RDF
• The Application
• Current/Future Work
• Demo
• Walkthrough
• Interactive
• Questions

3
The E-Culture Project

• Dutch BSIK project MultimediaN
• MN-N9C Application Pilot e-Culture
• VU (Guus Schreiber et.al.)
• CWI (Jacco van Ossenbruggen et.al.)
• UvA (Bob Wielinga, Jan Wielemaker, Victor de
  Boer)
• ICN, DEN
• Goals
• Golden Application for Semantic Web
• Improve "in context" search and presentation of
  search results by linking multiple Cultural
  Heritage collections
• Reusing existing background knowledge (rich
  domain!)
• Real users, real needs
• For now CH Professionals

4
Example Use Case

• Find Paintings from Monet
• Find Paintings from other painters with the same
  style as Monet

Monet
5
Example Use Case

• How can we find this painting?
• Are they related in some way?
• Metadata associated with the resource

• MUNCH, Edvard
• The Scream
• 1893
• Oil, tempera and pastel on cardboard
• 91 x 73.5 cm
• National Gallery, Oslo

6
Goals

• Currently
• Resources and Metadata is stored locally at the
  museums
• Little use of background knowledge
• Semi-standard format
• Our goal
• Distributed collections, accessible through Web
• (Re)Use distributed background knowledge for
  search and linking of resources
• Taxonomies, Ontologies, Structured Vocabularies
• Time/Space Reasoning
• Use (Semantic Web) Standards
• RDF(S)/OWL, XML, XHTML, SPARQL
• Multilinguality

7
RDF(S)/OWL

• Semantic Web standard for modelling of knowledge
• Triples (Subject, Predicate, Object)
• Namespaces (Who says what)
• (Mus1Painting001, vratitle, the Scream)
• RDFS adds classes, instances etc.
• OWL adds logic

vra title
Mus1 Painting001
The Scream
8
Labeled Graph
AAT Art Nouveau
Mus1 Painting001
glink has_style
vra title
The Scream
vra creator
UlanMunch, Edvard
Ulanstudent of
UlanThaulow, Fritz 
Ulandied_in
TGNNorway
TGNOslo
TGN partof
9
The (Meta)data

• Currently
• Collections Rijksmuseum A'dam (750),
  Artchive.com (3000), Rijksmuseum Volkenkunde
  (250.000),...
• Thesauri Getty AAT, TGN, ULAN SVCN, WordNet,
  ...
• 10M triples
• Conversion
• Thesauri to RDF
• Metadata to Thesaurus-concepts
• Manual and Automatic Enrichment of the
  annotations, more links. -gtTodo

10
Annotation Party
11
Architecture of the Demonstrator

• Open Web standards
• XML, XHTML, SVG, RDF/OWL
• SWI-Prologs semantic web package
• SPARQL interface, RDF/OWL partial reasoning
• AJAX for rich Web client interaction
• Semantic keyword suggestio
• Dynamic tree browser for structured taxonomies
• Java applets for other interaction types
• Picture point annotating image content

12
User Interface

• One backbone, multiple ways of presentation. User
  Interfaces
• Basic Search, Advanced Search, Timeline, Facet
  Browser
• Convey relevant information hidden in graph
  effectively to the user
• Exploit semantics to improve presentation
• time space
• User evaluation of the tool is an important part
  of the project-gt Todo

13
Semantic Web Challenge 2006

• Competition for Semantic Web End-user
  applications
• ISWC 2006
• First Prize!

TBL and Guus
14
Current/Future Work

• User Evaluation
• More links, more metadata
• Multilinguality
• More collections
• KIT
• Scalability
• Relation Search

15
Demo Time

• e-culture.multimedian.nl