@InProceedings{ishiwatari-EtAl:2017:Long,
  author    = {Ishiwatari, Shonosuke  and  Yao, Jingtao  and  Liu, Shujie  and  Li, Mu  and  Zhou, Ming  and  Yoshinaga, Naoki  and  Kitsuregawa, Masaru  and  Jia, Weijia},
  title     = {Chunk-based Decoder 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     = {1901--1912},
  abstract  = {Chunks (or phrases) once played a pivotal role in machine translation. By using
	a chunk rather than a word as the basic translation unit, local (intra-chunk)
	and global (inter-chunk) word orders and dependencies can be easily modeled.
	The chunk structure, despite its importance, has not been considered in the
	decoders used for neural machine translation (NMT). In this paper, we propose
	chunk-based decoders for (NMT), each of which consists of a chunk-level decoder
	and a word-level decoder. The chunk-level decoder models global dependencies
	while the word-level decoder decides the local word order in a chunk. To output
	a target sentence, the chunk-level decoder generates a chunk representation
	containing global information, which the word-level decoder then uses as a
	basis to predict the words inside the chunk. Experimental results show that our
	proposed decoders can significantly improve translation performance in a WAT
	'16 English-to-Japanese translation task.},
  url       = {http://aclweb.org/anthology/P17-1174}
}