@inproceedings{93cbdd9d17514545957688a1824c1706,
title = "EPR: a Neural Network for Automatic Feature Learning from Code for Defect Prediction",
abstract = "Software defect prediction plays a significant role in the software development cycle but suffers from many difficulties. In this paper we propose a novel deep learning model (including algorithms) called Extractor, Parser, and Reviewer (EPR) for defect prediction in software. Two different networks, recurrent neural networks (RNNs) and one-dimensional convolutional networks(ODCNs), are employed by the EPR for different purposes. RNN is utilized to extract contextual features to represent semantic dependencies between code tokens and ODCN acts as a parser to establish dependencies between semantic features. Meanwhile, the attention mechanism of the two networks is used as a reviewer to assign different weights from location information to the importance of the features, respectively. Our proposed model is validated by the PROMISE repository, and the results show that the proposed model in this paper significantly outperforms several existing algorithms.",
keywords = "attention mechanism, defect prediction, neural network",
author = "Dingbang Fang and Shaoying Liu and Ai Liu",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 21st International Conference on Software Quality, Reliability and Security, QRS 2021 ; Conference date: 06-12-2021 Through 10-12-2021",
year = "2021",
doi = "10.1109/QRS54544.2021.00059",
language = "英语",
series = "IEEE International Conference on Software Quality, Reliability and Security, QRS",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "482--492",
booktitle = "Proceedings - 2021 21st International Conference on Software Quality, Reliability and Security, QRS 2021",
address = "美国",
}