Code Edit Recommendation Using a Recurrent Neural Network

Abstract

When performing software evolution tasks, developers spend a significant amount of time looking for files to modify. By recommending files to modify, a code edit recommendation system reduces the developer's navigation time when conducting software evolution tasks. In this paper, we propose a code edit recommendation method using a recurrent neural network (CERNN). CERNN forms contexts that maintain the sequence of developers’ interactions to recommend files to edit and stops recommendations when the first recommendation becomes incorrect for the given evolution task. We evaluated our method by comparing it with the state-of-the-art method MI-EA that was developed based on the association rule mining technique. The result shows that our proposed method improves the average recommendation accuracy by approximately 5% over MI-EA (0.64 vs. 0.59 F-score).

Joint Embedding of Semantic and Statistical Features for Effective Code Search

“…To learn the deep statistical features of source code through deep learning methods [23], we employ semantic analysis and modeling on the source code. To extract the semantic information in the code as comprehensively as possible and eliminate the semantically irrelevant noise, this work proposes a source code feature extraction method.…”

Stability and Finite-Time Synchronization Analysis for Recurrent Neural Networks with Improved Integral-Type Time-Varying Delays

“…For the past few years, RNNs have been intensively investigated in various research fields such as machine learning, medical diagnosis, natural language processing, and model prediction [1][2][3][4][5][6][7][8]. Due to a certain transmission time of signal or information, time delays inevitably exist in RNNs, which may lead to oscillation, and even degradation for systems performances.…”