Some tasks are inferred based on the benchmarks list.
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.
A dataset for fine-grained entity typing of knowledge graph entities built from Freebase. It can be used to evaluate entity representations and also mention-level entity typing.