一句话：提出预训练框架 RepresentThemAll，学习缺陷报告的统一表示，并在四类下游任务上超越基线。
现有缺陷报告自动化研究通常为特定下游任务学习定制表示，导致多任务需训练多个模型，带来复杂性、成本与兼容性问题。本文提出 RepresentThemAll，一个可预训练并处理多任务的通用缺陷报告表示框架。其预训练采用两个精心设计的目标：动态掩码语言模型和名为“find yourself”的对比学习目标，以捕获通用缺陷报告语义。作者在重复缺陷报告检测、缺陷报告摘要、缺陷优先级预测和缺陷严重程度预测四个下游任务上评估，并在精心微调后与多种基线比较。实验结果显示，RepresentThemAll 在所有考虑的下游任务上均优于全部基线方法。
Deep learning techniques have shown promising performance in automated software maintenance tasks associated with bug reports. Currently, all existing studies learn the customized representation of bug reports for a specific downstream task. Despite early success, training multiple models for multiple downstream tasks faces three issues: complexity, cost, and compatibility, due to the customization, disparity, and uniqueness of these automated approaches. To resolve the above challenges, we propose RepresentThemAll, a pre-trained approach that can learn the universal representation of bug reports and handle multiple downstream tasks. Specifically, RepresentThemAll is a universal bug report framework that is pre-trained with two carefully designed learning objectives: one is the dynamic masked language model and another one is a contrastive learning objective, “find yourself”. We evaluate the performance of RepresentThemAll on four downstream tasks, including duplicate bug report detection, bug report summarization, bug priority prediction, and bug severity prediction. Our experimental results show that RepresentThemAll outperforms all baseline approaches on all considered downstream tasks after well-designed fine-tuning.
@inproceedings{FangZTJXS23,
title = {RepresentThemAll: A Universal Learning Representation of Bug Reports},
author = {Sen Fang and Tao Zhang and Youshuai Tan and He Jiang and Xin Xia and Xiaobing Sun},
booktitle = {ICSE},
year = {2023},
doi = {10.1109/icse48619.2023.00060}
}