@InProceedings{ionescu-popescu:2017:BEA,
  author    = {Ionescu, Radu Tudor  and  Popescu, Marius},
  title     = {Can string kernels pass the test of time in Native Language Identification?},
  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     = {224--234},
  abstract  = {We describe a machine learning approach for the 2017 shared task on Native
	Language Identification (NLI). The proposed approach combines several kernels
	using multiple kernel learning. While most of our kernels are based on
	character p-grams (also known as n-grams) extracted from essays or speech
	transcripts, we also use a kernel based on i-vectors, a low-dimensional
	representation of audio recordings, provided by the shared task organizers. For
	the learning stage, we choose Kernel Discriminant Analysis (KDA) over Kernel
	Ridge Regression (KRR), because the former classifier obtains better results
	than the latter one on the development set. In our previous work, we have used
	a similar machine learning approach to achieve state-of-the-art NLI results.
	The goal of this paper is to demonstrate that our shallow and simple approach
	based on string kernels (with minor improvements) can pass the test of time and
	reach state-of-the-art performance in the 2017 NLI shared task, despite the
	recent advances in natural language processing. We participated in all three
	tracks, in which the competitors were allowed to use only the essays (essay
	track), only the speech transcripts (speech track), or both (fusion track).
	Using only the data provided by the organizers for training our models, we have
	reached a macro F1 score of 86.95% in the closed essay track, a macro F1 score
	of 87.55% in the closed speech track, and a macro F1 score of 93.19% in the
	closed fusion track. With these scores, our team (UnibucKernel) ranked in the
	first group of teams in all three tracks, while attaining the best scores in
	the speech and the fusion tracks.},
  url       = {http://www.aclweb.org/anthology/W17-5024}
}