1. DIVE INTO THE EVENT-BASED
BROWSING OF LINKED HISTORICAL MEDIA
VICTOR DE BOER, JOHAN OOMEN, OANA INEL, LORA AROYO,
ELCO VAN STAVEREN, WERNER HELMICH AND DENNIS DE BEURS
EXPLORING HISTORICAL SOURCES WITH LANGUAGE
TECHNOLOGY: RESULTS AND PERSPECTIVES --8-9 DEC 2014
2. Clarin - Verrijkt Koninkrijk
National-
Socialist
29%
Named Entities
Social-
Democrat
21%
Protestant
13%
R-Catholic
Liberal
12%
12%
Communist
8%
Jewish
5%
Back-of-the-Book index
1. Dr. Loe de Jong’s seminal work on Dutch life in WW2 Scanned, OCR’ed, analyzed
2. Enriched through links with external datasets (Semantic Web)
3. Clarin - Dutch Ships and Sailors
Jur Leinenga:
Monsterrollen Noordelijke provincies
Matthias van Rossum Generale
Zeemonsterrollen VOC
KB
Delpher Dutch-Asiatic Shipping
(Huygens ING)
VOC Opvarenden (DANS
Easy)
6. Media researcher Lars Arve Røssland of the University of Bergen. (Photo: Andreas R. Graven)
DIGITAL HUMANITIES RESEARCHERS
7. 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
https://www.flickr.com/photos/drainrat/14779928998/
8.
9. DATA: OPENIMAGES.EU
Open videos Netherlands Institute for Sound and Vision
3000, mostly news broadcasts
10. DATA: DELPHER.NL
Scans of Radio bulletins (hand annotated)
1937 – 1984
1.5 Million OCR’ed and NErred
11. ENTITY EXTRACTION
ENTITY EXTRACTION
EVENTS CROWDSOURCING AND LINKING TO
CONCEPTS THROUGH CROWDTRUTH.ORG
LINKING EVENTS AND
CONCEPTS TO KEYFRAMES
SEGMENTATION & KEYFRAMES
CROWDTRUTH.ORG
18. Current work
USE COMMON VOCABULARIES
GTAA: GEMEENSCHAPPELIJKE THESAURUS
AUDIOVISUELE ARCHIEVEN
GEONAMES
ADD AND CLEAN DATA
ADD CROWD CORRECTIONS
EVALUATE