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.
@article{arxiv.1806.03743,
title = {Are All Languages Equally Hard to Language-Model?},
author = {Ryan Cotterell and Sabrina J. Mielke and Jason Eisner and Brian Roark},
journal= {arXiv preprint arXiv:1806.03743},
year = {2020}
}