一句话：系统比较多种 Transformer 预训练模型在缺陷分诊中的效果，发现 DeBERTa 在开发者与组件分配上最优。
缺陷报告管理是重要但耗时的维护任务，其中自动分诊需将缺陷分配给最适合的开发者或软件组件。已有方法多依赖缺陷报告的文本分类模型，但文本表示与模型表达能力有限，难以捕捉细微模式。本文在四个开源数据集上微调多种基于 Transformer 的预训练语言模型（如 BERT、CodeBERT、DeBERTa），数据集共覆盖 53 年开发历史、400 多名开发者和 150 多个组件，并针对开发者分配与组件分配进行定量和定性评估。结果表明，DeBERTa 在两个任务上最有效，性能差异统计显著；定性分析还显示各技术对不同类型缺陷报告具有独特优势。
Bug report management has been shown to be an important and time consuming software maintenance task. Often, the first step in managing bug reports is related to triaging a bug to the appropriate developer who is best suited to understand, localize, and fix the target bug. Additionally, assigning a given bug to a particular part of a software project can help to expedite the fixing process. However, despite the importance of these activities, they are quite challenging, where days can be spent on the manual triaging process. Past studies have attempted to leverage the limited textual data of bug reports to train text classification models that automate this process - to varying degrees of success. However, the textual representations and machine learning models used in prior work are limited by their expressiveness, often failing to capture nuanced textual patterns that might otherwise aid in the triaging process. Recently, large, transformer-based, pre-tained neural text representation techniques (i.e., large language models or LLMs) such as BERT and CodeBERT have achieved greater performance with simplified training procedures in several natural language processing tasks, including text classification. However, the potential for using these techniques to improve upon prior approaches for automated bug triaging is not well studied or understood. Therefore, in this paper we offer one of the first investigations that fine-tunes transformer-based language models for the task of bug triaging on four open source datasets, spanning a collective 53 years of development history with over 400 developers and over 150 software project components. Our study includes both a quantitative and qualitative analysis of effectiveness. Our findings illustrate that DeBERTa is the most effective technique across the triaging tasks of developer and component assignment, and the measured performance delta is statistically significant compared to other techniques. However, through our qualitative analysis, we also observe that each technique possesses unique abilities best suited to certain types of bug reports.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2310-06913,
title = {A Comparative Study of Transformer-Based Neural Text Representation Techniques on Bug Triaging},
author = {Atish Kumar Dipongkor and Kevin Moran},
booktitle = {ASE},
year = {2023},
doi = {10.1109/ase56229.2023.00217}
}