Companies increasingly use business process modeling for documenting and redesigning their operations.However, due to the size of such modeling initiatives, they often struggle with the quality assurance of their model collections. While many model properties can already be checked automatically, there is a notable gap of techniques for checking linguistic aspects such as naming conventions of process model elements. In this paper, we address this problem by introducing an automatic technique for detecting violations of naming conventions. This technique is based on text corpora and independent of linguistic resources such as WordNet.Therefore, it can be easily adapted to the broad set of languages for which corpora exist. We demonstrate the applicability of the technique by analyzing nine process model collections from practice, including over 27,000 labels and covering three di↵erent languages. The results of the evaluation show that our technique yields stable results and can reliably deal with ambiguous cases. In this way, this paper provides an important contribution to the field of automated quality assurance of conceptual models.