For our word2vec dataset, we used pre-calculated word2vec Embeddings trained on Google News, which can be downloaded here.
This was a count of the number of rotations, size changes,
and the number of overlaps or Embeddings of the shapes in each drawing, and provided a measure of"transformational complexity.".
The problem is that the powerful generic word Embeddings from giant databases like Wikipedia often miss nuances in language-
after all, every word becomes one single vector, so terms with multiple meanings can confuse even the smartest algorithms(think of“hack,” which can describe either what an ax does, a computer invasion, or an untalented writer).