ir.bib

@INPROCEEDINGS{cutting92scatter,
  AUTHOR = {Douglas Cutting and David Karger and Jan Pedersen and John Tukey},
  TITLE = {Scatter/Gather: A Cluster-based Approach to Browsing Large Document Collections},
  BOOKTITLE = {Proc. ACM SIGIR},
  YEAR = {1992},
  PAGES = {318--329},
  ANNOTE = {The introduction of interactive browsing technique that is computationally lighter (linear) than many of other clustering techniques.}
}

@PHDTHESIS{lewis92thesis,
  AUTHOR = {David D. Lewis},
  TITLE = {Representation and Learning in Information Retrieval},
  SCHOOL = {Department of Computer Science, University of Massachusetts},
  YEAR = {1992},
  ANNOTE = {Lewis ponders, why the representation of textual data seems to be so difficult. He constructs a basis for comparison of the representations, 'good' (possibly multiword) (index) terms and presents the phases of text classification using practical examples and results. Furthermore, the thesis contains a description of the Reuters-22173 corpus' anatomy.}
}

@BOOK{vanRijsbergen79,
  AUTHOR = {C. J. van Rijsbergen},
  TITLE = {Information Retrieval},
  PUBLISHER = {Butterworths},
  YEAR = {1980},
  EDITION = {2nd},
  URL = {http://www.dcs.gla.ac.uk/Keith/Preface.html},
  ANNOTE = {The author introduces similarity measures (Dice, Jaccard, cosini, overlap), similarity matrix, clustering, evaluation measures.}
}

@BOOK{salton89,
  AUTHOR = {Gerard Salton},
  TITLE = {Automatic Text Processing -- The Transformation, Analysis, and Retrieval of Information by Computer},
  PUBLISHER = {Addison--Wesley},
  YEAR = {1989},
  ANNOTE = {THE book. Presents the idea of document/term vectors.}
}