@InProceedings{zhang-EtAl:2017:EMNLP20174,
  author    = {Zhang, Xiao  and  Jiang, Yong  and  Peng, Hao  and  Tu, Kewei  and  Goldwasser, Dan},
  title     = {Semi-supervised Structured Prediction with Neural CRF Autoencoder},
  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     = {1701--1711},
  abstract  = {In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model
	for semi-supervised learning of sequential structured prediction problems. Our
	NCRF-AE consists of two parts: an encoder which is a CRF model enhanced by deep
	neural networks, and a decoder which is a generative model trying to
	reconstruct the input. Our model has a unified structure with different loss
	functions for labeled and unlabeled data with shared parameters. We developed a
	variation of the EM algorithm for optimizing both the encoder and the decoder
	simultaneously by decoupling their parameters. Our Experimental results over
	the Part-of-Speech (POS) tagging task on eight different languages, show that
	our model can outperform competitive systems in both supervised and
	semi-supervised scenarios.},
  url       = {https://www.aclweb.org/anthology/D17-1179}
}