E-Heritage and the VU Semantic Web group Guus Schreiber Computer Science VU University Amsterdam
Semantic VU Amsterdam 40 people, two groups: Web & Media (Schreiber), Knowledge Representation & Reasoning (van Harmelen) A few ongoing projects: –europeana.eu: EU culture portal –NL projects on access to cultural heritage: CHIP, Agora –EU NoTube: Web & TV semantic integration –PrestoPrime: user-generated annotations and content for TV archives –EU LarKC: platform for massive distributed incomplete reasoning
Characteristics of the Web AAA: Anyone can say Anything about Any Topic The Web is an open world It is impossible to enforce unique names The networl effect: a virtuous circle
The Web: resources and links URL Web link
The Semantic Web: typed resources and links URL Web link ULAN Henri Matisse Dublin Core creator Painting “Woman with hat SFMOMA
The myth of a unified vocabulary In large virtual collections there are always multiple vocabularies –In multiple languages Every vocabulary has its own perspective –You can’t just merge them But you can use vocabularies jointly by defining a limited set of links –“Vocabulary alignment” It is surprising what you can do with just a few links
Exempel use of vocabulary alignment “Tokugawa” SVCN period Edo SVCN is local in-house ethnology thesaurus AAT style/period Edo (Japanese period) Tokugawa AAT is Getty’s Art & Architecture Thesaurus
Architecture of a Semantic Web application Web pages, databases collections, tables, converters scrapers RDF store RDF files RDF query & inferencing Application
Demo using linked data (RPI, Hendler)
Search: WordNet patterns that increase recall without sacrificing precisions
Enriching the metadata
Resulting semantic annotation
Learning vocabulary alignments Example: learning relations between art styles in AAT and artists in ULAN through NLP of art historic texts –“Who are Impressionist painters?”
Personalized Rijksmuseum Interactive user modeling Recommendations of artworks and art topics
Mobile museum tour
Video tagging games