@InProceedings{zhang-EtAl:2017:I17-11,
  author    = {Zhang, Yue  and  Li, Zhenghua  and  Lang, Jun  and  Xia, Qingrong  and  Zhang, Min},
  title     = {Dependency Parsing with Partial Annotations: An Empirical Comparison},
  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     = {49--58},
  abstract  = {This paper describes and compares two straightforward approaches for dependency
	parsing with partial annotations (PA). The first approach is based on a
	forest-based training objective for two CRF parsers, i.e., a biaffine neural
	network graph-based parser (Biaffine) and a traditional log-linear graph-based
	parser (LLGPar). The second approach is based on the idea of constrained
	decoding for three parsers, i.e., a traditional linear graph-based parser
	(LGPar), a globally normalized neural network transition-based parser (GN3Par)
	and a traditional linear transition-based parser (LTPar). For the test phase,
	constrained decoding is also used for completing partial trees. We conduct
	experiments on Penn Treebank under three different settings for simulating PA,
	i.e., random, most uncertain, and divergent outputs from the five parsers. The
	results show that LLGPar is most effective in directly learning from PA, and
	other parsers can achieve best performance when PAs are completed into full
	trees by LLGPar.},
  url       = {http://www.aclweb.org/anthology/I17-1006}
}