DeepVS: An Efficient and Generic Approach for Source Code Modeling Usage

TL;DR

DeepVS is a deep learning-based code completion tool that uses BiGRU neural networks to provide accurate, real-time source code suggestions, including unseen tokens, demonstrating significant performance improvements in real-world software environments.

Contribution

This work introduces DeepVS, a novel end-to-end neural code completion system leveraging BiGRU networks for better generalization and real-time suggestions in IDEs.

Findings

Significant performance improvements over existing methods.

Capable of suggesting unseen code tokens.

Validated on ten real-world open-source projects.

Abstract

The source code suggestions provided by current IDEs are mostly dependent on static type learning. These suggestions often end up proposing irrelevant suggestions for a peculiar context. Recently, deep learning-based approaches have shown great potential in the modeling of source code for various software engineering tasks. However, these techniques lack adequate generalization and resistance to acclimate the use of such models in a real-world software development environment. This letter presents \textit{DeepVS}, an end-to-end deep neural code completion tool that learns from existing codebases by exploiting the bidirectional Gated Recurrent Unit (BiGRU) neural net. The proposed tool is capable of providing source code suggestions instantly in an IDE by using pre-trained BiGRU neural net. The evaluation of this work is two-fold, quantitative and qualitative. Through extensive evaluation on ten real-world open-source software systems, the proposed method shows significant performance enhancement and its practicality. Moreover, the results also suggest that \textit{DeepVS} tool is capable of suggesting zero-day (unseen) code tokens by learning coding patterns from real-world software systems.