@InProceedings{yang-EtAl:2017:Long,
  author    = {Yang, Zhilin  and  Hu, Junjie  and  Salakhutdinov, Ruslan  and  Cohen, William},
  title     = {Semi-Supervised QA with Generative Domain-Adaptive Nets},
  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     = {1040--1050},
  abstract  = {We study the problem of semi-supervised question answering----utilizing
	unlabeled text to boost the performance of question answering models. We
	propose a novel training framework, the \textit{Generative Domain-Adaptive
	Nets}. In this framework, we train a generative model to generate questions
	based on the unlabeled text, and combine model-generated questions with
	human-generated questions for training question answering models. We develop
	novel domain adaptation algorithms, based on reinforcement learning, to
	alleviate the discrepancy between the model-generated data distribution and the
	human-generated data distribution. Experiments show that our proposed framework
	obtains substantial improvement from unlabeled text.},
  url       = {http://aclweb.org/anthology/P17-1096}
}