@InProceedings{goyal-dyer-bergkirkpatrick:2017:Short,
  author    = {Goyal, Kartik  and  Dyer, Chris  and  Berg-Kirkpatrick, Taylor},
  title     = {Differentiable Scheduled Sampling for Credit Assignment},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {366--371},
  abstract  = {We demonstrate that a continuous relaxation of the argmax operation can be used
	to create a differentiable approximation to greedy decoding in
	sequence-to-sequence (seq2seq) models. By incorporating this approximation into
	the scheduled sampling training procedure--a well-known technique for
	correcting exposure bias--we introduce a new training objective that is
	continuous and differentiable everywhere and can provide informative gradients
	near points where previous decoding decisions change their value. By using a
	related approximation, we also demonstrate  a similar approach to sampled-based
	training. We show that our approach outperforms both standard cross-entropy
	training and scheduled sampling procedures in two sequence prediction tasks:
	named entity recognition and machine translation.},
  url       = {http://aclweb.org/anthology/P17-2058}
}