@InProceedings{cotterell-EtAl:2018:N18-21,
  author    = {Cotterell, Ryan  and  Mielke, Sebastian J.  and  Eisner, Jason  and  Roark, Brian},
  title     = {Are All Languages Equally Hard to Language-Model?},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {536--541},
  abstract  = {For general modeling methods applied to diverse languages, a natural question is: how well should we expect our models to work on languages with differing typological profiles? In this work, we develop an evaluation framework for fair cross-linguistic comparison of language models, using translated text so that all models are asked to predict approximately the same information. We then conduct a study on 21 languages, demonstrating that in some languages, the textual expression of the information is harder to predict with both n-gram and LSTM language models. We show complex inflectional morphology to be a cause of performance differences among languages.},
  url       = {http://www.aclweb.org/anthology/N18-2085}
}