Cross-linguistic differences and similarities in image descriptions

Emiel van Miltenburg, Desmond Elliott, Piek Vossen

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationInternational Conference on Natural Language Generation (INLG 2017)
PublisherAssociation for Computational Linguistics
Number of pages10
Publication statusPublished - 7 Sep 2017
Event10th International Conference on Natural Language Generation - Santiago de Compostela, Spain
Duration: 4 Sep 20177 Sep 2017


Conference10th International Conference on Natural Language Generation
Abbreviated titleINLG 2017
CitySantiago de Compostela
Internet address


  • cs.CL
  • cs.AI
  • cs.CV

Fingerprint Dive into the research topics of 'Cross-linguistic differences and similarities in image descriptions'. Together they form a unique fingerprint.

Cite this