@inproceedings{maximummarginrewardnetworksforlearning,
  title = {Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision},
  author = {Haoruo Peng and Ming-Wei Chang and Wen-tau Yih},
  year = {2017},
  booktitle = {EMNLP 2017 9},
  url = {https://aclanthology.org/D17-1252},
}