@InProceedings{qasemizadeh:2016:Computerm2016,
  author    = {QasemiZadeh, Behrang},
  title     = {A Study on the Interplay Between the Corpus Size and Parameters of a Distributional Model for Term Classification},
  booktitle = {Proceedings of the 5th International Workshop on Computational Terminology (Computerm2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {62--72},
  abstract  = {We propose and evaluate a method for identifying co-hyponym lexical units in a
	terminological resource. The principles of term recognition and distributional
	semantics are combined to extract terms from a similar category of concept.
	Given a set of candidate terms, random projections are employed to represent
	them as low-dimensional vectors. These vectors are derived automatically from
	the frequency of the co-occurrences of the candidate terms and words that
	appear within windows of text in their proximity (context-windows). In a
	$k$-nearest neighbours framework, these vectors are classified using a small
	set of manually annotated terms which exemplify concept categories. We then
	investigate the interplay between the size of the corpus that is used for
	collecting the co-occurrences and a number of factors that play roles in the
	performance of the proposed method: the configuration of context-windows for
	collecting co-occurrences, the selection of neighbourhood size ($k$), and the
	choice of similarity metric.},
  url       = {http://aclweb.org/anthology/W16-4708}
}