paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Stay professional and efficient

保持专业与高效
ASE Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering2020匹配度 1/10 · 该论文研究缺陷报告标题自动生成,属于软件工程/NLP for SE,使用Seq2Seq摘要模型,与用户关注的静态分析、程序分析、浮点程序分析、贝叶斯程序分析以及LLM/Agent改进分析等方向没有直接关系。引用 25 inbox
Songqiang Chen, Xiaoyuan Xie, Bangguo Yin, Yuanxiang Ji, Lin Chen, Baowen Xu
crossref: 2026-09-12

AI 速览

一句话:提出 iTAPE,将缺陷报告标题生成视为单句摘要任务,基于 Seq2Seq 自动生成高质量标题。

开源项目中的缺陷报告通常以列表形式展示标题和元数据,简洁准确的标题能帮助开发者快速理解缺陷核心,但实际标题质量参差不齐。为帮助报告者高效撰写高质量标题,作者提出 iTAPE,将标题生成形式化为单句摘要任务。针对领域特有挑战——缺少现成数据集以及低频人工命名 token 难以处理——iTAPE 构建相应数据并采用基于 Seq2Seq 的模型生成标题。实验与三种最新单句摘要工作对比,并结合人工评估,表明 iTAPE 能取得相当令人满意的结果。

问题
缺陷报告标题质量不一且撰写耗时,需要自动为缺陷报告生成简洁准确的标题。
方法
将标题生成建模为单句摘要任务,构建领域数据集并处理低频人工命名 token,使用 Seq2Seq 模型生成标题。
评估
与三种最新单句摘要方法进行对比,并开展人工评估,验证 iTAPE 的生成效果。
原文摘要(Abstract)

Bug reports in a repository are generally organized line by line in a list-view, with their titles and other meta-data displayed. In this list-view, a concise and precise title plays an important role that enables project practitioners to quickly and correctly digest the core idea of the bug, without carefully reading the corresponding details. However, the quality of bug report titles varies in open-source communities, which may be due to the limited time and unprofessionalism of authors. To help report authors efficiently draft good-quality titles, we propose a method, named iTAPE, to automatically generate titles for their bug reports. iTAPE formulates title generation into a one-sentence summarization task. By properly tackling two domain-specific challenges (i.e. lacking off-the-shelf dataset and handling the low-frequency human-named tokens), iTAPE then generates titles using a Seq2Seq-based model. A comprehensive experimental study shows that iTAPE can obtain fairly satisfactory results, in terms of the comparison with three latest one-sentence summarization works, as well as the feedback from human evaluation.

链接与引用

DOI 原文 ·

BibTeX
@inproceedings{paperbot6008,
  title = {Stay professional and efficient},
  author = {Songqiang Chen and Xiaoyuan Xie and Bangguo Yin and Yuanxiang Ji and Lin Chen and Baowen Xu},
  booktitle = {ASE},
  year = {2020},
  doi = {10.1145/3324884.3416538}
}