@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}
}
@phdthesis{Gollub,
  author    = {Gollub, Tim},
  title     = {Information Retrieval for the Digital Humanities},
  doi       = {10.25643/bauhaus-universitaet.4673},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220801-46738},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {177},
  abstract  = {In ten chapters, this thesis presents information retrieval technology which is tailored to the research activities that arise in the context of corpus-based digital humanities projects. The presentation is structured by a conceptual research process that is introduced in Chapter 1. The process distinguishes a set of five research activities: research question generation, corpus acquisition, research question modeling, corpus annotation, and result dissemination. Each of these research activities elicits different information retrieval tasks with special challenges, for which algorithmic approaches are presented after an introduction of the core information retrieval concepts in Chapter 2. A vital concept in many of the presented approaches is the keyquery paradigm introduced in Chapter 3, which represents an operation that returns relevant search queries in response to a given set of input documents. Keyqueries are proposed in Chapter 4 for the recommendation of related work, and in Chapter 5 for improving access to aspects hidden in the long tail of search result lists. With pseudo-descriptions, a document expansion approach is presented in Chapter 6. The approach improves the retrieval performance for corpora where only bibliographic meta-data is originally available. In Chapter 7, the keyquery paradigm is employed to generate dynamic taxonomies for corpora in an unsupervised fashion. Chapter 8 turns to the exploration of annotated corpora, and presents scoped facets as a conceptual extension to faceted search systems, which is particularly useful in exploratory search settings. For the purpose of highlighting the major topical differences in a sequence of sub-corpora, an algorithm called topical sequence profiling is presented in Chapter 9. The thesis concludes with two pilot studies regarding the visualization of (re)search results for the means of successful result dissemination: a metaphoric interpretation of the information nutrition label, as well as the philosophical bodies, which are 3D-printed search results.},
  subject      = {Information Retrieval},
  language  = {en}
}