☆ 4.7 Article

Dynamically Relative Position Encoding-Based Transformer for Automatic Code Edit

IEEE TRANSACTIONS ON RELIABILITY (2023)

Related references

Note: Only part of the references are listed.

Review Computer Science, Software Engineering

Automating App Review Response Generation Based on Contextual Knowledge

Cuiyun Gao et al.

Summary: The article introduces a novel neural network approach CoRe, which can naturally incorporate contextual knowledge without involving external tools, enhancing the relevance and accuracy of app review responses. Experimental results show that CoRe outperforms the state-of-the-art method in terms of the accuracy metric BLEU-4.

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY (2022)

Add to Collection

Article Computer Science, Software Engineering

CODIT: Code Editing With Tree-Based Neural Models

Saikat Chakraborty et al.

Summary: The way developers edit code tends to be repetitive, and researchers have tried to automate these repetitive changes. However, deep neural network based modeling for code changes introduces specific problems that need attention. This study proposes a tree-based neural network system to model source code changes and learn code change patterns.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2022)

Add to Collection

Article Computer Science, Software Engineering

ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking

Shangqing Liu et al.

Summary: Commit messages are records of code changes and help with program comprehension, but developers are often unwilling to write them. Automating the message generation process is necessary. By incorporating abstract syntax tree and combining retrieved and generated messages, accuracy can be improved.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2022)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

On the Importance of Building High-quality Training Datasets for Neural Code Search

Zhensu Sun et al.

Summary: The performance of neural code search heavily depends on the quality of the training data. Most existing code search datasets suffer from low quality and noisy queries, resulting in degraded performance in real-world applications. To address this issue, we propose a data cleaning framework consisting of two filters to improve the dataset quality and ensure semantic consistency of the queries. Experimental results demonstrate that training with the filtered dataset significantly improves the performance of neural code search models.

2022 ACM/IEEE 44TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2022) (2022)

Add to Collection

Review Computer Science, Software Engineering

A critical review on the evaluation of automated program repair systems

Kui Liu et al.

Summary: Automated Program Repair (APR) has gained attention in the past decade, with researchers proposing various evaluation metrics from the number of plausible patches to the number of correct patches. Bias in design decisions led to the proposal of eight evaluation metrics to fairly assess the performance of APR tools, aiming to reduce misleading computed metrics in the literature and highlight caveats in the community.

JOURNAL OF SYSTEMS AND SOFTWARE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

CoreGen: Contextualized Code Representation Learning for Commit Message Generation

Lun Yiu Nie et al.

Summary: Automatic generation of high-quality commit messages for code commits can greatly benefit software developers by facilitating their work and coordination. This paper introduces a novel Contextualized code representation learning strategy for commit message generation (CoreGen) that leverages contextual information behind code commit sequences, achieving at least 28.18% improvement in BLEU-4 score over baseline models. Future opportunities include training contextualized code representations on larger code corpus and adapting the framework to other code-to-text generation tasks.

NEUROCOMPUTING (2021)

Add to Collection

Article Computer Science, Software Engineering

SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair

Zimin Chen et al.

Summary: This paper introduces a novel end-to-end approach to program repair called SequenceR, using sequence-to-sequence learning to address the unlimited vocabulary issue in big code. The system, trained on carefully curated data, performs well in predicting and fixing bugs, demonstrating its effectiveness in real bug fixes and benchmark tests.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2021)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

DeepLocalize: Fault Localization for Deep Neural Networks

Mohammad Wardat et al.

Summary: Deep neural networks (DNNs) are essential in software systems, but they can have bugs. A proposed approach and tool aim to automatically detect and identify the root causes of DNN errors by analyzing historical trends in values propagated between layers. By enabling dynamic analysis of deep learning applications, faults can be detected and localized effectively.

2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

CURE: Code-Aware Neural Machine Translation for Automatic Program Repair

Nan Jiang et al.

Summary: CURE is a new NMT-based APR technique that outperforms existing approaches by pre-training a programming language model, designing a code-aware search strategy, and using subword tokenization technique to generate a smaller search space with more correct fixes.

2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Code Prediction by Feeding Trees to Transformers

Seohyun Kim et al.

Summary: The study focuses on improving code prediction accuracy in autocomplete systems using Transformers as the base neural architecture. By making the Transformer architecture aware of the syntactic structure of code, the system outperforms previous systems in next token prediction accuracy.

2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2021) (2021)

Add to Collection

Article Computer Science, Software Engineering

Deep Semantic Feature Learning for Software Defect Prediction

Song Wang et al.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2020)

Add to Collection

Article Computer Science, Software Engineering

CommtPst: Deep learning source code for commenting positions prediction

Yuan Huang et al.

JOURNAL OF SYSTEMS AND SOFTWARE (2020)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

DLFix: Context-based Code Transformation Automated Program Repair

Yi Li et al.

2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2020) (2020)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Software Visualization and Deep Transfer Learning for Effective Software Defect Prediction

Jinyin Chen et al.

2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2020) (2020)

Add to Collection

Proceedings Paper Automation & Control Systems

Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair

Haoye Tian et al.

2020 35TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING (ASE 2020) (2020)

Add to Collection

Article Computer Science, Software Engineering

How Well Do Change Sequences Predict Defects? Sequence Learning from Software Changes

Ming Wen et al.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2020)

Add to Collection

Article Computer Science, Software Engineering

An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation

Michele Tufano et al.

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

On Learning Meaningful Code Changes via Neural Machine Translation

Michele Tufano et al.

2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

A Comprehensive Study on Deep Learning Bug Characteristics

Md Johirul Islam et al.

ESEC/FSE'2019: PROCEEDINGS OF THE 2019 27TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (2019)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

DeepFL: Integrating Multiple Fault Diagnosis Dimensions for Deep Fault Localization

Xia Li et al.

PROCEEDINGS OF THE 28TH ACM SIGSOFT INTERNATIONAL SYMPOSIUM ON SOFTWARE TESTING AND ANALYSIS (ISSTA '19) (2019)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Neuro-Symbolic Program Corrector for Introductory Programming Assignments

Sahil Bhatia et al.

PROCEEDINGS 2018 IEEE/ACM 40TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE) (2018)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

A Closer Look at Real-World Patches

Kui Liu et al.

PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME) (2018)

Add to Collection

Article Computer Science, Software Engineering

Refactoring with Synthesis

Veselin Raychev et al.

ACM SIGPLAN NOTICES (2013)

Add to Collection

Article Computer Science, Software Engineering

A Graph-based Approach to API Usage Adaptation

Hoan Anh Nguyen et al.

ACM SIGPLAN NOTICES (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.