@InProceedings{zhang-EtAl:2017:EMNLP20173,
  author    = {Zhang, Zhirui  and  Liu, Shujie  and  Li, Mu  and  Zhou, Ming  and  Chen, Enhong},
  title     = {Stack-based Multi-layer Attention for Transition-based Dependency Parsing},
  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     = {1677--1682},
  abstract  = {Although sequence-to-sequence (seq2seq) network has achieved significant
	success in many NLP tasks such as machine translation and text summarization,
	simply applying this approach to transition-based dependency parsing cannot
	yield a comparable performance gain as in other state-of-the-art methods, such
	as stack-LSTM and head selection. In this paper, we propose a stack-based
	multi-layer attention model for seq2seq learning to better leverage structural
	linguistics information. In our method, two binary vectors are used to track
	the decoding stack in transition-based parsing, and multi-layer attention is
	introduced to capture multiple word dependencies in partial trees. We conduct
	experiments on PTB and CTB datasets, and the results show that our proposed
	model achieves state-of-the-art accuracy and significant improvement in labeled
	precision with respect to the baseline seq2seq model.},
  url       = {https://www.aclweb.org/anthology/D17-1175}
}