Time-Efficient Code Completion Model for the R Programming Language

Abstract

In this paper, we present a deep learning code completion model for the R programming language. We introduce several techniques to utilize language modeling based architecture in the code completion task. With these techniques, the model requires low resources, but still achieves high quality. We also present an evaluation dataset for the R programming language completion task. Our dataset contains multiple autocompletion usage contexts and that provides robust validation results. The dataset is publicly available.