@InProceedings{tomar-EtAl:2017:SCLeM,
  author    = {Tomar, Gaurav Singh  and  Duque, Thyago  and  T\"{a}ckstr\"{o}m, Oscar  and  Uszkoreit, Jakob  and  Das, Dipanjan},
  title     = {Neural Paraphrase Identification of Questions with Noisy Pretraining},
  booktitle = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {142--147},
  abstract  = {We present a solution to the problem of paraphrase identification of questions.
	We focus on a recent dataset of question pairs annotated with binary paraphrase
	labels and show that a variant of the decomposable attention model (replacing
	the word embeddings of the decomposable attention model of Parikh et al. 2016
	with character n-gram representations) results in accurate performance on this
	task, while being far simpler than many competing neural architectures.
	Furthermore, when the model is pretrained on a noisy dataset of automatically
	collected question paraphrases, it obtains the best reported performance on the
	dataset.},
  url       = {http://www.aclweb.org/anthology/W17-4121}
}