Blogs (1) >>
ASE 2019
Sun 10 - Fri 15 November 2019 San Diego, California, United States

It has been long suggested that commit messages can greatly facilitate code comprehension. However, developers may not write good commit messages in practice. Neural machine translation (NMT) has been suggested to automatically generate commit messages. Despite the efforts in improve NMT algorithms, the quality of the generated commit messages is not yet satisfactory. This paper, instead of improving NMT algorithms, suggests that proper preprocessing of code changes into concise inputs is quite critical to train NMT. We approach it with semantic analysis of code changes. We collect a real-world dataset with 50k+ commits of popular Java projects, and verify our idea with comprehensive experiments. The results show that preprocessing inputs with code semantic analysis can improve NMT significantly. This work sheds light to how to apply existing DNNs designed by the machine learning community, e.g., NMT models, to complete software engineering tasks.

Tue 12 Nov

Displayed time zone: Tijuana, Baja California change

15:20 - 16:00
Poster Session: Student Research CompetitionStudent Research Competition at Kensington Ballroom
15:20
40m
Boosting Neural Commit Message Generation with Code Semantic Analysis
Student Research Competition
Shuyao Jiang Fudan University
15:20
40m
Toward Practical Automatic Program Repair
Student Research Competition
Ali Ghanbari Iowa State University
15:20
40m
An Image-inspired and CNN-based Android Malware Detection Approach
Student Research Competition
Shao Yang Case Western Reserve University
15:20
40m
An Approach for Investigating Emotion Dynamics in Software Development
Student Research Competition
Krishna Neupane Rochester Institute of Technology
15:20
40m
A Machine Learning based Approach to Identify SQL Injection Vulnerabilities
Student Research Competition
Kevin Zhang Wayne State University
15:20
40m
Retrieve and Refine: Exemplar-based Neural Comment Generation
Student Research Competition
Bolin Wei Peking University
15:20
40m
Verifying Determinism in Sequential Programs
Student Research Competition
Rashmi Mudduluru University of Washington, Seattle
15:20
40m
User Preference Aware Multimedia Pricing Model using Game Theory and Prospect Theory for Wireless Communications
Student Research Competition
Krishna Murthy Kattiyan Ramamoorthy San Diego State University
15:20
40m
Empirical Study of Python Call Graph
Student Research Competition
Li Yu Nanjing University
15:20
40m
Towards Comprehensible Representation of Controllers using Machine Learning
Student Research Competition
Gargi Balasubramaniam Birla Institute of Technology and Science, Pilani, K K Birla Goa Campus
File Attached
15:20
40m
API Design Implications of Boilerplate Client Code
Student Research Competition
Daye Nam Carnegie Mellon University
15:20
40m
Compile-time detection of machine image sniping
Student Research Competition
Martin Kellogg University of Washington, Seattle
15:20
40m
Crowdsourced Report Generation via Bug Screenshot Understanding
Student Research Competition
Shengcheng Yu Nanjing University, China
File Attached

Wed 13 Nov

Displayed time zone: Tijuana, Baja California change

13:40 - 15:20
Student Research Competition - Selected Presentations (Undergraduate)Student Research Competition at South Park
Chair(s): Jin L.C. Guo McGill University, Jie M. Zhang University College London, UK
13:40
15m
Crowdsourced Report Generation via Bug Screenshot Understanding
Student Research Competition
Shengcheng Yu Nanjing University, China
File Attached
13:55
15m
Towards Comprehensible Representation of Controllers using Machine Learning
Student Research Competition
Gargi Balasubramaniam Birla Institute of Technology and Science, Pilani, K K Birla Goa Campus
File Attached
14:10
15m
Empirical Study of Python Call Graph
Student Research Competition
Li Yu Nanjing University
14:25
15m
A Machine Learning based Approach to Identify SQL Injection Vulnerabilities
Student Research Competition
Kevin Zhang Wayne State University
14:40
15m
Boosting Neural Commit Message Generation with Code Semantic Analysis
Student Research Competition
Shuyao Jiang Fudan University