@InProceedings{rama-ccoltekin:2017:BEA,
  author    = {Rama, Taraka  and  \c{C}\"{o}ltekin, \c{C}a\u{g}rı},
  title     = {Fewer features perform well at Native Language Identification task},
  booktitle = {Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {255--260},
  abstract  = {This paper describes our results at the NLI shared task 2017.  We participated
	in essays, speech, and fusion task that uses text, speech, and i-vectors for
	the task of identifying the native language of the given input. In the essay
	track, a linear SVM system using word bigrams and character 7-grams performed
	the best. In the speech track, an LDA classifier based only on i-vectors
	performed better than a combination system using text features from speech
	transcriptions and i-vectors. In the fusion task, we experimented with systems
	that used combination of i-vectors with higher order n-grams features,
	combination of i-vectors with word unigrams, a mean probability ensemble, and a
	stacked ensemble system. Our finding is that word unigrams in combination with
	i-vectors achieve higher score than systems trained with larger number of
	\emph{n}-gram features.  Our best-performing systems achieved F1-scores of
	87.16%, 83.33% and 91.75% on the essay track, the speech track and the fusion
	track respectively.},
  url       = {http://www.aclweb.org/anthology/W17-5028}
}