ShapeWorld is used to generate the data for this project
ShapeWorld is a framework which allows to specify generators for abstract, visually grounded language data (or just visual data).
It was written by Alexander Kuhnle and Ann Copestake (April 2017) and adapted by Laura Graesser for this project.
If you use ShapeWorld in your work, please cite:
ShapeWorld: A new test methodology for multimodal language understanding (arXiv) Alexander Kuhnle and Ann Copestake (April 2017)
For more details, please see the original repository