@InProceedings{iyer-EtAl:2017:Long,
  author    = {Iyer, Srinivasan  and  Konstas, Ioannis  and  Cheung, Alvin  and  Krishnamurthy, Jayant  and  Zettlemoyer, Luke},
  title     = {Learning a Neural Semantic Parser from User Feedback},
  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     = {963--973},
  abstract  = {We present an approach to rapidly and easily build natural language interfaces
	to databases for new domains, whose performance improves over time based on
	user feedback, and requires minimal intervention. To achieve this, we adapt
	neural sequence models to map utterances directly to SQL with its full
	expressivity, bypassing any intermediate meaning representations. These models
	are immediately deployed online to solicit feedback from real users to flag
	incorrect queries. Finally, the popularity of SQL facilitates gathering
	annotations for incorrect predictions using the crowd, which is directly used
	to improve our models. This complete feedback loop, without intermediate
	representations or database specific engineering, opens up new ways of building
	high quality semantic parsers. Experiments suggest that this approach can be
	deployed quickly for any new target domain, as we show by learning a semantic
	parser for an online academic database from scratch.},
  url       = {http://aclweb.org/anthology/P17-1089}
}