Did the original paper do any shuffle controls? Given your results I suspect such controls would have failed. For some reason this is not standard practice in AI research, despite it being extremely standard in other disciplines.
They use a WordNet hierarchy to verify their orthogonality results at scale, but doesn’t look like they do any other shuffle controls.
Did the original paper do any shuffle controls? Given your results I suspect such controls would have failed. For some reason this is not standard practice in AI research, despite it being extremely standard in other disciplines.
They use a WordNet hierarchy to verify their orthogonality results at scale, but doesn’t look like they do any other shuffle controls.