@InProceedings{zhang-EtAl:2017:I17-13,
  author    = {Zhang, Boliang  and  Lu, Di  and  Pan, Xiaoman  and  Lin, Ying  and  Abudukelimu, Halidanmu  and  Ji, Heng  and  Knight, Kevin},
  title     = {Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {362--372},
  abstract  = {Current supervised name tagging approaches are inadequate for most low-resource
	languages due to the lack of annotated data and actionable linguistic
	knowledge. 
	All supervised learning methods (including deep neural networks (DNN)) are
	sensitive to noise and thus they are not quite                          portable
	without
	massive
	clean
	annotations. We found that the F-scores of DNN-based name taggers drop rapidly
	(20%-30%) when we replace clean manual annotations with noisy annotations in
	the training data. We propose a new solution to incorporate many
	non-traditional language universal resources that are readily available but
	rarely explored in the Natural Language Processing (NLP) community, such as the
	World Atlas of Linguistic Structure, CIA names, PanLex and survival guides. 
	We acquire and encode various types of non-traditional 
	linguistic resources into a DNN name tagger. Experiments on three low-resource
	languages show that feeding linguistic knowledge 
	can make DNN significantly more robust to noise, achieving 8%-22% absolute
	F-score gains on name tagging without using any human annotation},
  url       = {http://www.aclweb.org/anthology/I17-1037}
}