@article{learningonlinealignmentswithcontinuous,
  title = {Learning Online Alignments with Continuous Rewards Policy Gradient},
  author = {Yuping Luo and Chung-Cheng Chiu and Navdeep Jaitly and Ilya Sutskever},
  year = {2016},
  eprint = {1608.01281},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1608.01281v1},
}