@InProceedings{jauhiainen-linden-jauhiainen:2016:VarDial3,
  author    = {Jauhiainen, Tommi  and  Lind\'{e}n, Krister  and  Jauhiainen, Heidi},
  title     = {HeLI, a Word-Based Backoff Method for Language Identification},
  booktitle = {Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {153--162},
  abstract  = {In this paper we describe the Helsinki language identification method, HeLI,
	and the resources we created for and used in the 3rd edition of the
	Discriminating between Similar Languages (DSL) shared task, which was organized
	as part of the VarDial 2016 workshop. The shared task comprised of a total of 8
	tracks, of which we participated in 7. The shared task had a record number of
	participants, with 17 teams providing results for the closed track of the test
	set A. Our system reached the 2nd position in 4 tracks (A closed and open, B1
	open and B2 open) and in this paper we are focusing on the methods and data
	used for those tracks. We describe our word-based backoff method in
	mathematical notation. We also describe how we selected the corpus we used in
	the open tracks.},
  url       = {http://aclweb.org/anthology/W16-4820}
}

