@InProceedings{kawakami-dyer-blunsom:2017:Long,
  author    = {Kawakami, Kazuya  and  Dyer, Chris  and  Blunsom, Phil},
  title     = {Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling},
  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     = {1492--1502},
  abstract  = {Fixed-vocabulary language models fail to account for one of the most
	characteristic statistical facts of natural language: the frequent creation and
	reuse of new word types. Although character-level language models offer a
	partial solution in that they can create word types not attested in the
	training corpus, they do not capture the ``bursty'' distribution of such words.
	In this paper, we augment a hierarchical LSTM language model that generates
	sequences of word tokens character by character with a caching mechanism that
	learns to reuse previously generated words. 
	To validate our model we construct a new open-vocabulary language modeling
	corpus (the Multilingual Wikipedia Corpus; MWC) from comparable Wikipedia
	articles in 7 typologically diverse languages and demonstrate the effectiveness
	of our model across this range of languages.},
  url       = {http://aclweb.org/anthology/P17-1137}
}