@InProceedings{junczysdowmunt-grundkiewicz:2017:I17-1,
  author    = {Junczys-Dowmunt, Marcin  and  Grundkiewicz, Roman},
  title     = {An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing},
  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     = {120--129},
  abstract  = {In this work, we explore multiple neural architectures adapted for the task of
	automatic post-editing of machine translation output.  We focus on neural
	end-to-end models that combine both inputs $\mt$ (raw MT output) and $\src$
	(source language input) in a single neural architecture, modeling $\{\mt,
	\src\} \rightarrow \pe$ directly. Apart from that, we investigate the influence
	of hard-attention models which seem to be well-suited for monolingual tasks, as
	well as combinations of both ideas.
	We report results on data sets provided during the WMT-2016 shared task on
	automatic post-editing and can demonstrate that dual-attention models that
	incorporate all available data in the APE scenario in a single model improve on
	the best shared task system and on all other published results after the shared
	task. Dual-attention models that are combined with hard attention  remain
	competitive despite applying fewer changes to the input.},
  url       = {http://www.aclweb.org/anthology/I17-1013}
}