What goes into a word: generating image descriptions with top-down spatial knowledge

Mehdi Ghanimifard, Simon Dobnik. What goes into a word: generating image descriptions with top-down spatial knowledge. In Kees van Deemter, Chenghua Lin, Hiroya Takamura, editors, Proceedings of the 12th International Conference on Natural Language Generation, INLG 2019, Tokyo, Japan, October 29 - November 1, 2019. pages 540-551, Association for Computational Linguistics, 2019. [doi]

Abstract

Abstract is missing.