@InProceedings{chu-EtAl:2017:EACLshort,
  author    = {Chu, Zewei  and  Wang, Hai  and  Gimpel, Kevin  and  McAllester, David},
  title     = {Broad Context Language Modeling as Reading Comprehension},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {52--57},
  abstract  = {Progress in text understanding has been driven by large datasets that test
	particular capabilities, like recent datasets for reading comprehension
	(Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al.,
	2016), a word prediction task requiring broader context than the immediate
	sentence. We view LAMBADA as a reading comprehension problem and apply
	comprehension models based on neural networks. Though these models are
	constrained to choose a word from the context, they improve the state of the
	art on LAMBADA from 7.3% to 49%. We analyze 100 instances, finding that neural
	network readers perform well in cases that involve selecting a name from the
	context based on dialogue or discourse cues but struggle when coreference
	resolution or external knowledge is needed.},
  url       = {http://www.aclweb.org/anthology/E17-2009}
}