Business process modelers need to have expertise and knowledge of the domain that may not always be available to them. Therefore, they may benefit from tools that mine collections of existing processes and recommend element(s) to be added to a new process that they are constructing. In this paper, we present a method for process autocompletion at design time, that is based on the semantic similarity of sub-processes. By converting sub-processes to textual paragraphs and encoding them as numerical vectors, we can find semantically similar ones, and thereafter recommend the next element. To achieve this, we leverage a state-of-the-art technique for embedding natural language as vectors. We evaluate our approach on open source and proprietary datasets and show that our technique is accurate for processes in various domains.