@InProceedings{malmasi-EtAl:2017:BEA,
  author    = {Malmasi, Shervin  and  Evanini, Keelan  and  Cahill, Aoife  and  Tetreault, Joel  and  Pugh, Robert  and  Hamill, Christopher  and  Napolitano, Diane  and  Qian, Yao},
  title     = {A Report on the 2017 Native Language Identification Shared 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     = {62--75},
  abstract  = {Native Language Identification (NLI) is the task of automatically identifying
	the native language (L1) of an individual based on their language production in
	a learned language. It is typically framed as a classification task where the
	set of L1s is known a priori. Two previous shared tasks on NLI have been
	organized where the aim was to identify the L1 of learners of English based on
	essays (2013) and spoken responses (2016) they provided during a standardized
	assessment of academic English proficiency. The 2017 shared task combines the
	inputs from the two prior tasks for the first time. There are three tracks: NLI
	on the essay only, NLI on the spoken response only (based on a transcription of
	the response and i-vector acoustic features), and NLI using both responses. We
	believe this makes for a more interesting shared task while building on the
	methods and results from the previous two shared tasks. In this paper, we
	report the results of the shared task. A total of 19 teams competed across the
	three different sub-tasks. The fusion track showed that combining the written
	and spoken responses provides a large boost in prediction accuracy. Multiple
	classifier systems (e.g. ensembles and meta-classifiers) were the most
	effective in all tasks, with most based on traditional classifiers (e.g. SVMs)
	with lexical/syntactic features.},
  url       = {http://www.aclweb.org/anthology/W17-5007}
}