Kummer, Robert (2013). Intelligent Information Access to Linked Data - Weaving the Cultural Heritage Web. PhD thesis, Universität zu Köln.


Download (8MB)


The subject of the dissertation is an information alignment experiment of two cultural heritage information systems (ALAP): The Perseus Digital Library and Arachne. In modern societies, information integration is gaining importance for many tasks such as business decision making or even catastrophe management. It is beyond doubt that the information available in digital form can offer users new ways of interaction. Also, in the humanities and cultural heritage communities, more and more information is being published online. But in many situations the way that information has been made publicly available is disruptive to the research process due to its heterogeneity and distribution. Therefore integrated information will be a key factor to pursue successful research, and the need for information alignment is widely recognized. ALAP is an attempt to integrate information from Perseus and Arachne, not only on a schema level, but to also perform entity resolution. To that end, technical peculiarities and philosophical implications of the concepts of identity and co-reference are discussed. Multiple approaches to information integration and entity resolution are discussed and evaluated. The methodology that is used to implement ALAP is mainly rooted in the fields of information retrieval and knowledge discovery. First, an exploratory analysis was performed on both information systems to get a first impression of the data. After that, (semi-)structured information from both systems was extracted and normalized. Then, a clustering algorithm was used to reduce the number of needed entity comparisons. Finally, a thorough matching was performed on the different clusters. ALAP helped with identifying challenges and highlighted the opportunities that arise during the attempt to align cultural heritage information systems.

Item Type: Thesis (PhD thesis)
CreatorsEmailORCIDORCID Put Code
Kummer, Robertrokummer@gmail.comUNSPECIFIEDUNSPECIFIED
URN: urn:nbn:de:hbz:38-53048
Date: 2013
Language: English
Faculty: Faculty of Arts and Humanities
Divisions: Faculty of Arts and Humanities > Fächergruppe 2: Archäologie, Altertumskunde und Kulturen des Mittelmeerraums > Archäologisches Institut > Abteilung für Historisch-kulturwissenschaftliche Informationsverarbeitung
Subjects: Data processing Computer science
Uncontrolled Keywords:
information integrationEnglish
entity resolutionEnglish
record linkageEnglish
artificial intelligenceEnglish
machine learningEnglish
semantic webEnglish
cidoc crmEnglish
Date of oral exam: 11 July 2012
NameAcademic Title
Thaller, ManfredProf. Dr.
Förtsch, ReinhardProf. Dr.
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/5304


Downloads per month over past year


Actions (login required)

View Item View Item