@InProceedings{garmash-monz:2016:COLING,
  author    = {Garmash, Ekaterina  and  Monz, Christof},
  title     = {Ensemble Learning for Multi-Source Neural Machine Translation},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1409--1418},
  abstract  = {In this paper we describe and evaluate methods to perform ensemble prediction
	in neural machine translation (NMT). We compare two methods of ensemble set
	induction: sampling parameter initializations for an NMT system, which is a
	relatively established method in NMT (Sutskever et al., 2014), and NMT systems
	translating from different source languages into the same target language,
	i.e., multi-source ensembles, a method recently introduced by Firat et al.
	(2016). We are motivated by the observation that for different language pairs
	systems make different types of mistakes. We propose several methods with
	different degrees of parameterization to combine individual predictions of NMT
	systems so that they mutually compensate for each other’s mistakes and
	improve overall performance. We find that the biggest improvements can be
	obtained from a context-dependent weighting scheme for multi-source ensembles.
	This result offers stronger support for the linguistic motivation of using
	multi-source ensembles than previous approaches. Evaluation is carried out for
	German and French into English translation. The best multi-source ensemble
	method achieves an improvement of up to 2.2 BLEU points over the strongest
	single-source ensemble baseline, and a 2 BLEU improvement over a multi-source
	ensemble baseline.},
  url       = {http://aclweb.org/anthology/C16-1133}
}