Towards better ML-based software services: an investigation of source code engineering impact

Article Computer Science, Hardware & Architecture

SeTransformer: A Transformer-Based Code Semantic Parser for Code Comment Generation

Zheng Li et al.

Summary: Automated code comment generation technologies can help developers understand code intent, reducing the cost of software maintenance and revision. In this article, a novel improved-Transformer-based comment generation method is proposed, which solves the long-term dependence problem and extracts both text and structure information from program code. Experimental results show that the method outperforms state-of-the-art baselines in performance and comment quality.

IEEE TRANSACTIONS ON RELIABILITY (2023)

Add to Collection

Article Computer Science, Software Engineering

Source code change analysis with deep learning based programming model

Babita Pathik et al.

Summary: This paper proposes an impact analysis method using Attention BiLSTM to detect changes and their affected parts in object-oriented software systems. The experimental results show that this method efficiently detects code changes, significantly improving change detection accuracy compared to other conventional models.

AUTOMATED SOFTWARE ENGINEERING (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

LineVD: Statement-level Vulnerability Detection using Graph Neural Networks

David Hin et al.

Summary: Current machine-learning based software vulnerability detection methods primarily focus on function-level detection, lacking the ability to indicate specific lines of code contributing to vulnerabilities. This study proposes a novel deep learning framework, LineVD, which utilizes graph neural networks and a transformer-based model to detect vulnerabilities at the statement-level, significantly improving prediction performance.

2022 MINING SOFTWARE REPOSITORIES CONFERENCE (MSR 2022) (2022)

Add to Collection

Article Computer Science, Software Engineering

SeCNN: A semantic CNN parser for code comment generation

Zheng Li et al.

Summary: This paper introduces a novel parser SeCNN for code comment generation, which uses CNN and various new components to capture the semantic information of source code and address the long-dependency issue. Experimental results demonstrate that SeCNN outperforms five state-of-the-art baselines in terms of performance and execution time cost.

JOURNAL OF SYSTEMS AND SOFTWARE (2021)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

TYPILUS: Neural Type Hints

Miltiadis Allamanis et al.

PROCEEDINGS OF THE 41ST ACM SIGPLAN CONFERENCE ON PROGRAMMING LANGUAGE DESIGN AND IMPLEMENTATION (PLDI '20) (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

A Neural Model for Generating Natural Language Summaries of Program Subroutines

Alexander LeClair et al.

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

Add to Collection

Article Computer Science, Information Systems

Seml: A Semantic LSTM Model for Software Defect Prediction

Hongliang Liang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Software Engineering

code2vec: Learning Distributed Representations of Code

Uri Alon et al.

PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL (2019)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

AST-Based Deep Learning for Detecting Malicious PowerShell

Gili Rusak et al.

PROCEEDINGS OF THE 2018 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS'18) (2018)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

Towards String-to-Tree Neural Machine Translation

Roee Aharoni et al.

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2 (2017)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Suggesting Accurate Method and Class Names

Miltiadis Allamanis et al.

2015 10TH JOINT MEETING OF THE EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND THE ACM SIGSOFT SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE 2015) PROCEEDINGS (2015)

Add to Collection

Towards better ML-based software services: an investigation of source code engineering impact

Related references

Export Citation

Share Paper