@InProceedings{yang-EtAl:2017:EMNLP20172,
  author    = {Yang, Baosong  and  Wong, Derek F.  and  Xiao, Tong  and  Chao, Lidia S.  and  Zhu, Jingbo},
  title     = {Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation},
  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     = {1432--1441},
  abstract  = {This paper proposes a hierarchical attentional neural translation model which
	focuses on enhancing source-side hierarchical representations by covering both
	local and global semantic information using a bidirectional tree-based encoder.
	To maximize the predictive likelihood of target words, a weighted variant of an
	attention mechanism is used to balance the attentive information between
	lexical and phrase vectors. Using a tree-based rare word encoding, the proposed
	model is extended to sub-word level to alleviate the out-of-vocabulary (OOV)
	problem. Empirical results reveal that the proposed model significantly
	outperforms sequence-to-sequence attention-based and tree-based neural
	translation models in English-Chinese translation tasks.},
  url       = {https://www.aclweb.org/anthology/D17-1150}
}