@InProceedings{peng-chang-yih:2017:EMNLP2017, author = {Peng, Haoruo and Chang, Ming-Wei and Yih, Wen-tau}, title = {Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, month = {September}, year = {2017}, address = {Copenhagen, Denmark}, publisher = {Association for Computational Linguistics}, pages = {2368--2378}, url = {https://www.aclweb.org/anthology/D17-1252} }