paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Automatically Annotating Sentences for Task-specific Bug Report Summarization

为任务特定缺陷报告摘要自动标注句子
ASE 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)2021匹配度 1/10 · 该论文研究缺陷报告摘要的自动标注,属于软件工程/开发者工具领域,但未涉及静态分析、形式化验证、浮点程序分析、贝叶斯程序分析,也未涉及 LLM/Agent 与程序分析的交叉。引用 0 inbox
Akalanka Galappaththi, John Anvik, Rafat Bin Islam
crossref: 2026-09-12

AI 速览

一句话:提出一种自动标注缺陷报告句子的方法,使项目成员能按任务特定信息需求生成摘要。

缺陷报告往往因开发者之间的对话以及各类 DevOps 工具的评论而变得冗长,因此需要自动摘要。现有自动摘要方法以尽可能接近金标准摘要为目标,作者认为这一目标有误。论文主张研究者应开发自动缺陷报告标注方法,让项目成员能够根据自身任务特定的信息需求生成摘要。为此,论文提出了一种这样的自动标注方法,但摘要未给出具体的技术细节与评估结果。

问题
缺陷报告因开发者对话和 DevOps 工具产生大量评论而变得冗长;现有自动摘要方法以逼近金标准摘要为目标,未考虑项目成员任务特定的信息需求。
方法
提出一种自动标注缺陷报告句子的方法,使项目成员能根据自身任务特定的信息需求生成摘要。
评估
摘要未给出具体评估方式与结果,仅提出该自动标注方法及相关研究立场。
原文摘要(Abstract)

There is a need to summarize bug reports as they can become long due to many comments from conversations between developers and various DevOps tools. Although automated approaches to bug report summarization have been developed, we believe they aim at the wrong target - getting as close as possible to a gold-standard summary. Instead, researchers should create automated bug report annotation approaches that allow project members to create summaries based on their task-specific information needs. We present such an approach.

链接与引用

DOI 原文 ·

BibTeX
@inproceedings{paperbot6500,
  title = {Automatically Annotating Sentences for Task-specific Bug Report Summarization},
  author = {Akalanka Galappaththi and John Anvik and Rafat Bin Islam},
  booktitle = {ASE},
  year = {2021},
  doi = {10.1109/ase51524.2021.9678554}
}