@InProceedings{li-EtAl:2017:Long,
  author    = {Li, Junhui  and  Xiong, Deyi  and  Tu, Zhaopeng  and  Zhu, Muhua  and  Zhang, Min  and  Zhou, Guodong},
  title     = {Modeling Source Syntax for Neural Machine Translation},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {688--697},
  abstract  = {Even though a linguistics-free sequence to sequence model in neural machine
	translation (NMT) has certain capability of implicitly learning syntactic
	information of source sentences, this paper shows that source syntax can be
	explicitly incorporated into NMT effectively to provide further improvements.
	Specifically, we linearize parse trees of source sentences to obtain structural
	label sequences. On the basis, we propose three different sorts of encoders to
	incorporate source syntax into NMT: 1) Parallel RNN encoder that learns word
	and label annotation vectors parallelly; 2) Hierarchical RNN encoder that
	learns word and label annotation vectors in a two-level hierarchy; and 3) Mixed
	RNN encoder that stitchingly learns word and label annotation vectors over
	sequences where words and labels are mixed. Experimentation on
	Chinese-to-English translation demonstrates that all the three proposed
	syntactic encoders are able to improve translation accuracy. It is interesting
	to note that the simplest RNN encoder, i.e., Mixed RNN encoder yields the best
	performance with an significant improvement of 1.4 BLEU points. Moreover, an
	in-depth analysis from several perspectives is provided to reveal how source
	syntax benefits NMT.},
  url       = {http://aclweb.org/anthology/P17-1064}
}