一句话：提出 EALink 预训练框架，以更少参数高效准确地恢复 issue-commit 链接，并大幅超越现有方法。
issue-commit 链接是一类软件可追溯性链接，对软件开发与维护任务至关重要，但常因开发者忘记或未能创建标签而缺失。现有基于深度学习和预训练模型的自动恢复方法虽表现不俗，但仍存在四个主要问题，阻碍其在大规模软件项目中有效恢复链接。本文提出高效准确的预训练框架 EALink，其模型参数远少于现有预训练方法，训练和恢复效率更高；同时设计多种技术提升恢复准确率。作者构建大规模数据集并进行广泛实验。结果表明，EALink 在多项评价指标上大幅超越当前最优方法，提升幅度为 15.23% 至 408.65%，且训练与推理开销低数个数量级。
Issue-commit links, as a type of software traceability links, play a vital role in various software development and maintenance tasks. However, they are typically deficient, as developers often forget or fail to create tags when making commits. Existing studies have deployed deep learning techniques, including pretrained models, to improve automatic issue-commit link recovery. Despite their promising performance, we argue that previous approaches have four main problems, hindering them from recovering links in large software projects. To overcome these problems, we propose an efficient and accurate pre-trained framework called EALink for issue-commit link recovery. EALink requires much fewer model parameters than existing pre-trained methods, bringing efficient training and recovery. Moreover, we design various techniques to improve the recovery accuracy of EALink. We construct a large-scale dataset and conduct extensive experiments to demonstrate the power of EALink. Results show that EALink outperforms the state-of-the-art methods by a large margin (15.23%-408.65%) on various evaluation metrics. Meanwhile, its training and inference overhead is orders of magnitude lower than existing methods. We provide our implementation and data at https://github.com/KDEGroup/EALink.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2308-10759,
title = {EALink: An Efficient and Accurate Pre-Trained Framework for Issue-Commit Link Recovery},
author = {Chenyuan Zhang and Yanlin Wang and Zhao Wei and Yong Xu and Juhong Wang and Hui Li and Rongrong Ji},
booktitle = {ASE},
year = {2023},
doi = {10.1109/ase56229.2023.00059}
}