一句话：提出基于注意力神经网络的SATD检测与解释方法
自认技术债（SATD）是技术债的一种子类型，指开发者在软件开发过程中有意引入的技术债。它虽然能带来短期收益，但往往需要在后续以更高成本偿还，例如引入软件缺陷或增加软件复杂度。该论文关注SATD的检测与解释问题，标题表明其采用基于注意力机制的神经网络方法，从代码/注释等软件制品中识别SATD并给出解释。所给摘要仅交代了SATD的定义与危害，未提供具体模型结构、数据集、评价指标和实验结果，因此无法进一步总结其关键结果。
Self-Admitted Technical Debt (SATD) is a sub-type of technical debt. It is introduced to represent such technical debts that are intentionally introduced by developers in the process of software development. While being able to gain short-term benefits, the introduction of SATDs often requires to be paid back later with a higher cost, e.g., introducing bugs to the software or increasing the complexity of the software.
@inproceedings{paperbot5945,
title = {Detecting and explaining self-admitted technical debts with attention-based neural networks},
author = {Xin Wang and Jin Liu and Li Li and Xiao Chen and Xiao Liu and Hao Wu},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3416583}
}