@InProceedings{guu-EtAl:2017:Long,
  author    = {Guu, Kelvin  and  Pasupat, Panupong  and  Liu, Evan  and  Liang, Percy},
  title     = {From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {1051--1062},
  abstract  = {Our goal is to learn a semantic parser that maps natural language utterances
	into executable programs when only indirect supervision is available: examples
	are labeled with the correct execution result, but not the program itself.
	Consequently, we must search the space of programs for those that output the
	correct result, while not being misled by \emph{spurious programs}: incorrect
	programs that coincidentally output the correct result. We connect two common
	learning paradigms, reinforcement learning (RL) and maximum marginal likelihood
	(MML), and then present a new learning algorithm that combines the strengths of
	both. The new algorithm guards against spurious programs by combining the
	systematic search traditionally employed in MML with the randomized exploration
	of RL, and by updating parameters such that probability is spread more evenly
	across consistent programs. We apply our learning algorithm to a new neural
	semantic parser and show significant gains over existing state-of-the-art
	results on a recent context-dependent semantic parsing task.},
  url       = {http://aclweb.org/anthology/P17-1097}
}