@InProceedings{yimam-EtAl:2017:RANLP,
  author    = {Yimam, Seid Muhie  and  \v{S}tajner, Sanja  and  Riedl, Martin  and  Biemann, Chris},
  title     = {Multilingual and Cross-Lingual Complex Word Identification},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {813--822},
  abstract  = {Complex Word Identification (CWI) is an important task in lexical
	simplification and text accessibility. Due to the lack of CWI datasets,
	previous works largely depend on Simple English Wikipedia and edit histories
	for obtaining ‘gold standard’ annotations, which are of doubtable quality,
	and limited only to English. We collect complex words/phrases (CP) for English,
	German and Spanish, annotated by both native and non-native speakers, and
	propose language independent features that can be used to train multilingual
	and cross-lingual CWI models. We show that the performance of cross-lingual CWI
	systems (using a model trained on one language and applying it on the other
	languages) is comparable to the performance of monolingual CWI systems.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_104}
}