@article{VoelskeGollubHagenetal.,
  author    = {V{\"o}lske, Michael and Gollub, Tim and Hagen, Matthias and Stein, Benno},
  title     = {A keyquery-based classification system for CORE},
  series = {D-Lib Magazine},
  journal   = {D-Lib Magazine},
  doi       = {10.1045/november14-voelske},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20170426-31662},
  abstract  = {We apply keyquery-based taxonomy composition to compute a classification system for the CORE dataset, a shared crawl of about 850,000 scientific papers. Keyquery-based taxonomy composition can be understood as a two-phase hierarchical document clustering technique that utilizes search queries as cluster labels: In a first phase, the document collection is indexed by a reference search engine, and the documents are tagged with the search queries they are relevant—for their so-called keyqueries. In a second phase, a hierarchical clustering is formed from the keyqueries within an iterative process. We use the explicit topic model ESA as document retrieval model in order to index the CORE dataset in the reference search engine. Under the ESA retrieval model, documents are represented as vectors of similarities to Wikipedia articles; a methodology proven to be advantageous for text categorization tasks. Our paper presents the generated taxonomy and reports on quantitative properties such as document coverage and processing requirements.},
  subject      = {Massendaten},
  language  = {en}
}