@InProceedings{zampieri-EtAl:2017:NLPTEA,
  author    = {Zampieri, Marcos  and  Malmasi, Shervin  and  Paetzold, Gustavo  and  Specia, Lucia},
  title     = {Complex Word Identification: Challenges in Data Annotation and System Performance},
  booktitle = {Proceedings of the 4th Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA 2017)},
  month     = {December},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {59--63},
  abstract  = {This paper revisits the problem of complex word identification (CWI) following
	up the SemEval CWI shared task. We use ensemble classifiers to investigate how
	well computational methods can discriminate between complex and non-complex
	words. Furthermore, we analyze the classification performance to understand
	what makes lexical complexity challenging. Our findings show that most systems
	performed poorly on the SemEval CWI dataset, and one of the reasons for that is
	the way in which human annotation was performed.},
  url       = {http://www.aclweb.org/anthology/W17-5910}
}