ASE 2024
Sun 27 October - Fri 1 November 2024 Sacramento, California, United States
Thu 31 Oct 2024 14:15 - 14:30 at Magnoila - Code and issue report Chair(s): Baishakhi Ray

High-quality and appropriate commit messages help developers to quickly understand and track code evolution, which is crucial for the collaborative development and maintenance of software. To relieve developers of the burden of writing commit messages, researchers have proposed various techniques to generate commit messages automatically, among which learning-based techniques have proven to be promising. However, the performance of these learning-based techniques is generally low on the BLEU metric. Some reasons for low BLEU have been summarized, including the effect of noisy data, the truncation mechanism of the model, insufficient utilization of context information, etc. Through extensive empirical analysis, we find that the diversity of commits may also be one of the factors that affect the performance of existing learning-based techniques. As a result of this diversity, there are mainly two types of commit messages in the real world: one offers a superficial summary of relatively simple code changes (called the “explicit” commit message), and the other summarizes complex code changes from a global perspective, reflecting the nature or intent behind the changes (called the “implicit” commit message). Our empirical study shows that generating implicit commit messages is more challenging for these techniques, and the models have limited ability to generalize when facing cross-category generation. To fully verify these conclusions, we build a model that identifies explicit and implicit commit messages automatically, and then use it to construct our datasets. Next, we evaluate the ability of state-of-the-art learning-based techniques to generate explicit and implicit commit messages and the generalization capacity of the models. Finally, we propose a “Diversion” strategy to take advantage of the generating performance of specific models. Experimental results show that our approach improves the performance of most learning-based techniques in generating commit messages.

Thu 31 Oct

Displayed time zone: Pacific Time (US & Canada) change

13:30 - 15:00
Code and issue reportResearch Papers at Magnoila
Chair(s): Baishakhi Ray Columbia University, New York; AWS AI Lab
13:30
15m
Talk
PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
Research Papers
Ziyou Jiang Institute of Software at Chinese Academy of Sciences, Lin Shi Beihang University, Guowei Yang University of Queensland, Qing Wang Institute of Software at Chinese Academy of Sciences
DOI Pre-print
13:45
15m
Talk
Understanding Code Changes Practically with Small-Scale Language Models
Research Papers
Cong Li Zhejiang University; Ant Group, Zhaogui Xu Ant Group, Peng Di Ant Group, Dongxia Wang Zhejiang University, Zheng Li Ant Group, Qian Zheng Ant Group
14:00
15m
Talk
DRMiner: Extracting Latent Design Rationale from Jira Issue LogsACM SigSoft Distinguished Paper Award
Research Papers
Jiuang Zhao Beihang University, Zitian Yang Beihang University, Li Zhang Beihang University, Xiaoli Lian Beihang University, China, Donghao Yang Beihang University, Xin Tan Beihang University
14:15
15m
Talk
An Empirical Study on Learning-based Techniques for Explicit and Implicit Commit Messages Generation
Research Papers
Zhiquan Huang Sun Yat-sen University, Yuan Huang Sun Yat-sen University, Xiangping Chen Sun Yat-sen University, Xiaocong Zhou School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China, Changlin Yang Sun Yat-sen University, Zibin Zheng Sun Yat-sen University
14:30
15m
Talk
RCFG2Vec: Considering Long-Distance Dependency for Binary Code Similarity Detection
Research Papers
Weilong Li School of Computer Science and Engineering,Sun Yat-sen University, Jintian Lu College of Computer Science and Engineering, Jishou University, Ruizhi Xiao School of Computer Science and Engineering,Sun Yat-sen University, Pengfei Shao China Southern Power Grid Digital Grid Group Information and Telecommunication Technology Co., Ltd., Shuyuan Jin School of Computer Science and Engineering,Sun Yat-sen University
14:45
15m
Talk
ChatBR: Automated assessment and improvement of bug report quality using ChatGPT
Research Papers
Lili Bo Yangzhou University, wangjie ji Yangzhou University, Xiaobing Sun Yangzhou University, Ting Zhang Singapore Management University, Xiaoxue Wu Yangzhou University, Ying Wei Yangzhou University