@phdthesis{Schoeneberg2014,
  author    = {Sch{\"o}neberg, Hendrik},
  title     = {Semiautomatische Metadaten-Extraktion und Qualit{\"a}tsmanagement in Workflow-Systemen zur Digitalisierung historischer Dokumente},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-104878},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2014},
  abstract  = {Performing Named Entity Recognition on ancient documents is a time-consuming, complex and error-prone manual task. It is a prerequisite though to being able to identify related documents and correlate between named entities in distinct sources, helping to precisely recreate historic events. In order to reduce the manual effort, automated classification approaches could be leveraged. Classifying terms in ancient documents in an automated manner poses a difficult task due to the sources' challenging syntax and poor conservation states. This thesis introduces and evaluates approaches that can cope with complex syntactial environments by using statistical information derived from a term's context and combining it with domain-specific heuristic knowledge to perform a classification. Furthermore this thesis demonstrates how metadata generated by these approaches can be used as error heuristics to greatly improve the performance of workflow systems for digitizations of early documents.},
  subject      = {Klassifikation},
  language  = {de}
}