@InProceedings{barteld:2017:EACLSRW17,
  author    = {Barteld, Fabian},
  title     = {Detecting spelling variants in non-standard texts},
  booktitle = {Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {11--22},
  abstract  = {Spelling variation in non-standard language, e.g. computer-mediated
	communication and historical texts, is usually treated as a deviation from a
	standard spelling, e.g. 2mr as an non-standard spelling for tomorrow.
	Consequently, in normalization -- the standard approach of dealing with
	spelling variation -- so-called non-standard words are mapped to their
	corresponding standard words. However, there is not always a corresponding
	standard word. This can be the case for single types (like emoticons in
	computer-mediated communication) or a complete language, e.g. texts from
	historical languages that did not develop to a standard variety. The approach
	presented in this
	thesis proposal deals with spelling variation in absence of reference to a
	standard. The task is to detect pairs of types that are variants of the same
	morphological word. An approach for spelling-variant detection is presented,
	where pairs of potential spelling variants are generated with Levenshtein
	distance and subsequently filtered by supervised machine learning. The
	approach is evaluated on historical Low German texts. Finally, further
	perspectives are discussed.},
  url       = {http://www.aclweb.org/anthology/E17-4002}
}