@InProceedings{wieting-gimpel:2017:Long,
  author    = {Wieting, John  and  Gimpel, Kevin},
  title     = {Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings},
  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     = {2078--2088},
  abstract  = {We consider the problem of learning general-purpose, paraphrastic sentence
	embeddings, revisiting the setting of Wieting et al. (2016b). While they found
	LSTM recurrent networks to underperform word averaging, we present several
	developments that together produce the opposite conclusion. These include
	training on sentence pairs rather than phrase pairs, averaging states to
	represent sequences, and regularizing aggressively. These improve LSTMs in both
	transfer learning and supervised settings. We also introduce a new recurrent
	architecture, the Gated Recurrent Averaging Network, that is inspired by
	averaging and LSTMs while outperforming them both. We analyze our learned
	models, finding evidence of preferences for particular parts of speech and
	dependency relations.},
  url       = {http://aclweb.org/anthology/P17-1190}
}