Greater theorizing of methods in the computational humanities is needed for epistemological and interpretive clarity, and therefore the maturation of the field. In this paper, we frame such modeling work as engaging in translation work from a cultural, linguistic domain into a computational, mathematical domain, and back again. Translators benefit from articulating the theory of their translation process, and so do computational humanists in their work -- to ensure internal consistency, avoid subtle yet consequential translation errors, and facilitate interpretive transparency. Our contribution in this paper is to lay out a particularly consequential dimension of the lack of theorizing and the sorts of translation errors that emerge in our modeling practices as a result. Along these lines we introduce the idea of semiotic complexity as the degree to which the meaning of some text may vary across interpretive lenses, and make the case that dominant modeling practices -- especially around evaluation -- commit a translation error by treating semiotically complex data as semiotically simple when it seems epistemologically convenient by conferring superficial clarity. We then lay out several recommendations for researchers to better account for these epistemological issues in their own work.