@InProceedings{vanmiltenburg-elliott-vossen:2017:INLG2017,
  author    = {van Miltenburg, Emiel  and  Elliott, Desmond  and  Vossen, Piek},
  title     = {Cross-linguistic differences and similarities in image descriptions},
  booktitle = {Proceedings of the 10th International Conference on Natural Language Generation},
  month     = {September},
  year      = {2017},
  address   = {Santiago de Compostela, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {21--30},
  abstract  = {Automatic image description systems are commonly trained and evaluated on large
	image description datasets. Recently, researchers have started to collect such
	datasets for languages other than English. An unexplored question is how
	different these datasets are from English and, if there are any differences,
	what causes them to differ. This paper provides a cross-linguistic comparison
	of Dutch, English, and German image descriptions. We find that these
	descriptions are similar in many respects, but the familiarity of crowd workers
	with the subjects of the images has a noticeable influence on the specificity
	of the descriptions.},
  url       = {http://www.aclweb.org/anthology/W17-3503}
}