dive+ @patch2015 workshop @iui2015
TRANSCRIPT
Open, Connected & Smart Heritage: Towards New Cultural Commons
http://lora-aroyo.org ! http://slideshare.net/laroyo ! @laroyo
massive amount of digital content to explore …
http://lora-aroyo.org ! http://slideshare.net/laroyo ! @laroyo
at some point it all looks the same …
http://lora-aroyo.org ! http://slideshare.net/laroyo ! @laroyo
SMART
We need more of this
Johan Oomen, Lora Aroyo (2011). Crowdsourcing in the Cultural Heritage Domain: OpportuniCes and Challenges, hDp://www.iisi.de/fileadmin/IISI/upload/2011/p138_oomen.pdf
CONNECTED OPEN
Digital Humani;es perform interpreta(on of texts and other media
interpretaCons deal with perspecCves
http://lora-aroyo.org ! http://slideshare.net/laroyo ! @laroyo
we need …. support of mul6ple perspec6ves
http://lora-aroyo.org ! http://slideshare.net/laroyo ! @laroyo
CrowdTruth.org
Machine-‐Human Computa;on for Harnessing Perspec;ves in Seman;c Interpreta;on
Oana Inel, Khalid Khamkham, Ta6ana Cristea, Anca Dumitrache, Arne Rutjes , Jelle v.d Ploeg , Lukasz Romaszko, Lora Aroyo, Robert-‐Jan Sips
HUMAN DISAGREEMENT IS ESSENTIAL IN HELPING MACHINES WITH SEMANTIC INTERPRETATION!
Lora Aroyo, Chris Welty: Truth is a Lie: 7 Myths about Human Annota6on, AI Magazine 2015. (In press)
• Machine Pre-processing: op6mizing crowdsourcing
• Micro-task Templates: reuse & op6miza6on
• CrowdTruth Analytics: disagreement-‐based metrics
CrowdTruth SoFware Components: Machines & Crowds Workflow
Ø Novel approach to ground truth data collec6on & evalua6on Ø PROV for tracking versions of data Ø Reusability in variety of annota;on tasks & domains with text,
image, video (thinking about sound)
Oana Inel, Khalid Khamkham, Ta6ana Cristea, Arne Rutjes, Jelle van der Ploeg, Lora Aroyo, Robert-‐Jan Sips, Anca Dumitrache and Lukasz Romaszko: Crowd Truth: Machine-‐Human Computa6on Framework for Harnessing Disagreement in Gathering Annotated Data. ISWC-‐RBDS
2014.
CrowdTruth SoFware: Crowdsourcing Analy;cs
Lora Aroyo, Chris Welty: The Three Sides of CrowdTruth. J. Human Computa6on. 1(1). 2014.
• Open source: h]ps://github.com/CrowdTruth • Web service: h]p://stable.crowdtruth.org
CrowdTruth SoFware: Crowdsourcing Analy;cs
dive.beeldengeluid.nl
In Digital Hermeneu;cs
Use Case: Event-‐centric Explora6on
Sound & Vision and Royal Library
OPENIMAGES.EU • 3000 videos • NL Ins6tute for Sound & Vision • mostly news broadcasts
DELPHER.NL • 1.5 Million Scans of • Radio bulle6ns • (hand annotated) • 1937 – 1984
ENTITY EXTRACTION
CROWDTRUTH.ORG
ENTITY EXTRACTION
EVENTS CROWDSOURCING AND LINKING TO CONCEPTS THROUGH CROWDTRUTH.ORG
SEGMENTATION & KEYFRAMES
LINKING EVENTS AND CONCEPTS TO KEYFRAMES
SIMPLE EVENT MODEL (SEM), OPENANNOTATION (OA) AND SKOS
DIVE:MEDIA OBJECT
SEM:EVENT
SEM:PLACE
SEM:TIME
SEM:ACTOR
SKOS:CONCEPT
OA:ANNOTATION
LINKS TO EUROPEANA (MULTILINGUAL) LINKS TO DBPEDIA
Erp, M. van; Oomen, J.; Segers, R.; Akker, C. van de; Aroyo, L.; Jacobs, G.; Legêne, S; Meij, L. van der;O ssenbruggen, J.R. van; Schreiber, G. Automa6c Heritage Metadata Enrichment with Historic Events Museums and the Web 2011 h]p://www.museumsandtheweb.com/mw2011/papers/automa6c_heritage_metadata_enrichment_with_hi
CLIOPATRIA TRIPLE STORE
130K TRIPLES (FOR NOW) SPARQL ENDPOINT
HTTP://ECULTURE.CS.VU.NL:8877/DIVE/HOME
EXPLORATIVE SEARCH
• Erp, M. van; Oomen, J.; Segers, R.; Akker, C. van de; Aroyo, L.; Jacobs, G.; Legêne, S; Meij, L. van der;O ssenbruggen, J.R. van; Schreiber, G. Automatic Heritage Metadata Enrichment with Historic Events Museums and the Web 2011 http://www.museumsandtheweb.com/mw2011/papers/automatic_heritage_metadata_enrichment_with_hi
h]ps://w
ww.flickr.com
/photos/drainrat/14779928998/
The Team: Victor de Boer, Oana Inel, Lora Aroyo, Johan Oomen, Jaap Blom, Werner Helmich & Dennis De Beurs, Chiel van den Akker, Susan Legêne, Huub Wijfies, Carlos
Mar6nez Or6z
dive.beeldengeluid.nl