The benchmarks section lists all benchmarks using a given dataset or any of
its variants. We use variants to distinguish between results evaluated on
slightly different versions of the same dataset. For example, ImageNet 32⨉32
and ImageNet 64⨉64 are variants of the ImageNet dataset.
This resource is designed to allow for research into Natural Language Generation. In particular, with neural data-to-text approaches although it is not limited to these.