@InProceedings{zhang-cheng-lapata:2017:EACLlong,
  author    = {Zhang, Xingxing  and  Cheng, Jianpeng  and  Lapata, Mirella},
  title     = {Dependency Parsing as Head Selection},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {665--676},
  abstract  = {Conventional graph-based dependency parsers guarantee a tree
	  structure both during training and inference. Instead, we formalize
	  dependency parsing as the problem of independently selecting the
	  head of each word in a sentence. Our model which we call
	  \textsc{DeNSe} (as shorthand for {\bf De}pendency {\bf N}eural {\bf
	    Se}lection) produces a distribution over possible heads for each
	  word using features obtained from a bidirectional recurrent neural
	  network. Without enforcing structural constraints during training,
	  \textsc{DeNSe} generates (at inference time) trees for the
	  overwhelming majority of sentences, while non-tree outputs can be
	  adjusted with a maximum spanning tree algorithm.  We evaluate
	  \textsc{DeNSe} on four languages (English, Chinese, Czech, and
	  German) with varying degrees of non-projectivity. Despite the
	  simplicity of the approach, our parsers are on par with the state of
	  the art.\footnote{Our code is available at
	    \url{http://github.com/XingxingZhang/dense\_parser}.}},
  url       = {http://www.aclweb.org/anthology/E17-1063}
}