Automatic code completion is the task of predicting the next tokens or completing a statement based on a developer’s coding context. Auto-complete methods aim at helping developers accomplish their programming tasks faster and more efficiently through decreasing the effort needed to find and type the next correct tokens. Several studies have shown auto-complete feature is among the most prominent features in IDEs. However, IDEs mostly provide recommendations based on alphabetical or historical order of usage, regardless of the relevance of predictions to the task at hand. Although ML-based models are promising, current research approaches fail to tackle several challenges such as out-of-vocabulary words and long-range dependencies. In this lecture, we will discuss an RNN-based deep model for code completion. We will also discuss when code completion methods fail.
Papers to be discussed in this session are: [1], [2].
The course contents are copyrighted (c) 2018,2019,2020 - onwards by TU Delft and their respective authors and licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.