@InProceedings{yimam-EtAl:2017:I17-2,
  author    = {Yimam, Seid Muhie  and  \v{S}tajner, Sanja  and  Riedl, Martin  and  Biemann, Chris},
  title     = {CWIG3G2 - Complex Word Identification Task across Three Text Genres and Two User Groups},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {401--407},
  abstract  = {Complex word identification (CWI) is an important task in text accessibility.
	However, due to the scarcity of CWI datasets, previous studies have only
	addressed this problem on Wikipedia sentences and have solely taken into
	account the needs of non-native English speakers. We collect a new CWI dataset
	(CWIG3G2) covering three text genres News, WikiNews, and Wikipedia) annotated
	by both native and non-native English speakers. Unlike previous datasets, we
	cover single words, as well as complex phrases, and present them for judgment
	in a paragraph context. We present the first study on cross-genre and
	cross-group CWI, showing measurable influences in native language and genre
	types.},
  url       = {http://www.aclweb.org/anthology/I17-2068}
}