@InProceedings{dalvi-EtAl:2017:I17-1,
  author    = {Dalvi, Fahim  and  Durrani, Nadir  and  Sajjad, Hassan  and  Belinkov, Yonatan  and  Vogel, Stephan},
  title     = {Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder},
  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     = {142--151},
  abstract  = {End-to-end training makes the neural machine translation (NMT) architecture
	simpler, yet elegant compared to traditional statistical machine translation
	(SMT). However, little is known about linguistic patterns of morphology, syntax
	and semantics learned during the training of NMT systems, and more importantly,
	which parts of the architecture are responsible for learning each of these
	phenomenon. In this paper we i) analyze how much morphology an NMT decoder
	learns, and ii) investigate whether injecting target morphology in the decoder
	helps it to produce better translations. To this end we present three methods:
	i) simultaneous translation, ii) joint-data learning, and iii) multi-task
	learning. Our results show that explicit morphological information helps the
	 decoder learn target language morphology and improves the translation 
	quality by 0.2--0.6 BLEU points.},
  url       = {http://www.aclweb.org/anthology/I17-1015}
}