A problem with Semantic Modeling

I don't like the way performance of semantic models is reported. It's impossible to compare results between papers. The results are as much a function of corpus choice and pre-processing as they are of the algorithm itself.

I think in my reporting of any new or unique set of data, I should submit results from basic DSMs - GloVe, LSA, CBOW, skip-gram, BEAGLE. That would demonstrate the effect I'm presenting relative to all of the models when under the same constraints of corpus choice and pre-processing.