Augmenting Machine Learning with Information Retrieval to Recommend Real Cloned Code Methods for Code Completion

Abstract

Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones accumulated in these repositories hence represent often repeated functionalities and are candidates for reuse in an exploratory or rapid development. In previous work, we introduced DeepClone, a deep neural network model trained by fine tuning GPT-2 model over the BigCloneBench dataset to predict code clone methods. The probabilistic nature of DeepClone output generation can lead to syntax and logic errors that requires manual editing of the output for final reuse. In this paper, we propose a novel approach of applying an information retrieval (IR) technique on top of DeepClone output to recommend real clone methods closely matching the predicted output. We have quantitatively evaluated our strategy, showing that the proposed approach significantly improves the quality of recommendation.

References in corpus (8)

• A Deep Reinforced Model for Abstractive Summarization
• The Curious Case of Neural Text Degeneration
• Neural Text Generation with Unlikelihood Training
• Adversarial Learning for Neural Dialogue Generation
• Hierarchical Neural Story Generation
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
• On End-to-End Program Generation from User Intention by Deep Neural Networks
• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models