@InProceedings{ma-hovy:2017:I17-1,
  author    = {Ma, Xuezhe  and  Hovy, Eduard},
  title     = {Neural Probabilistic Model for Non-projective MST Parsing},
  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     = {59--69},
  abstract  = {In this paper, we propose a probabilistic parsing model that defines a proper
	conditional probability distribution over non-projective
	dependency trees for a given sentence, using neural representations as inputs.
	The neural network architecture is based on bi-directional LSTMCNNs,
	which automatically benefits from both word- and character-level
	representations, by using a combination of bidirectional LSTMs and CNNs. On top
	of the neural network, we introduce a probabilistic structured layer, defining
	a conditional log-linear model over non-projective trees. By exploiting
	Kirchhoff’s Matrix-Tree Theorem (Tutte, 1984), the partition functions and
	marginals can be computed efficiently, leading to a straightforward end-to-end
	model training procedure via back-propagation. We evaluate our model on 17
	different datasets, across 14 different languages. Our parser achieves
	state-of-the-art parsing performance on nine datasets.},
  url       = {http://www.aclweb.org/anthology/I17-1007}
}