@InProceedings{vania-lopez:2017:Long,
  author    = {Vania, Clara  and  Lopez, Adam},
  title     = {From Characters to Words to in Between: Do We Capture Morphology?},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {2016--2027},
  abstract  = {Words can be represented by composing the representations of subword units such
	as word segments, characters, and/or character n-grams. While such
	representations are effective and may capture the morphological regularities of
	words, they have not been systematically compared, and it is not understood how
	they interact with different morphological typologies. On a language modeling
	task, we present experiments that systematically vary (1) the basic unit of
	representation, (2) the composition of these representations, and (3) the
	morphological typology of the language modeled. Our results extend previous
	findings that character representations are effective across typologies, and we
	find that a previously unstudied combination of character trigram
	representations composed with bi-LSTMs outperforms most others. But we also
	find room for improvement: none of the character-level models match the
	predictive accuracy of a model with access to true morphological analyses, even
	when learned from an order of magnitude more data.},
  url       = {http://aclweb.org/anthology/P17-1184}
}