@InProceedings{mykowiecka-marciniak-rychlik:2016:Computerm2016,
  author    = {Mykowiecka, Agnieszka  and  Marciniak, Malgorzata  and  Rychlik, Piotr},
  title     = {Recognition of non-domain phrases in automatically extracted lists of terms},
  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     = {12--20},
  abstract  = {In the paper, we address the problem of recognition of non-domain phrases in
	terminology lists obtained with an automatic term extraction tool. We focus on
	identification of multi-word phrases that are general terms and discourse
	function expressions. We tested several methods based on domain corpora
	comparison and a method based on contexts of phrases identified in a large
	corpus of general language. We compared the results of the methods to manual
	annotation. The results show that the task is quite hard as the inter-annotator
	agreement is low. Several tested methods achieved similar overall results,
	although the phrase ordering varied between methods. The most successful method
	with the precision about 0.75 at the half of the tested list was the context
	based method using a modified contextual diversity coefficient.},
  url       = {http://aclweb.org/anthology/W16-4703}
}