软件工程句子对中冲突与重复检测的数据增强
Data Augmentation for Conflict and Duplicate Detection in Software Engineering Sentence Pairs
AI总结:
本文针对软件工程句子对的冲突与重复检测任务,改编通用数据增强技术并提出三种针对软件需求文本的新增强技术,在六个数据集上验证了其显著效果,同时指出在数据集平衡时可能产生负面影响。
摘要:
本文探讨了使用文本数据增强技术,通过句子对分类来增强软件工程任务中的冲突与重复检测。研究改编了打乱、回译和改写等通用增强技术,并针对软件需求文本提出了名词-动词替换、目标词元替换和施事者-动作替换等新数据增强技术。在六个软件文本数据集上进行了全面的实证分析,以识别句子对之间的冲突与重复。结果表明,数据增强技术对所有软件句子对文本数据集的性能有显著影响。另一方面,在数据集相对平衡的情况下,使用增强技术可能对分类性能产生负面影响。
英文摘要:
This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification. The study adapts generic augmentation techniques such as shuffling, back translation, and paraphrasing and proposes new data augmentation techniques such as Noun-Verb Substitution, target-lemma replacement and Actor-Action Substitution for software requirement texts. A comprehensive empirical analysis is conducted on six software text datasets to identify conflicts and duplicates among sentence pairs. The results demonstrate that data augmentation techniques have a significant impact on the performance of all software pair text datasets. On the other hand, in cases where the datasets are relatively balanced, the use of augmentation techniques may result in a negative effect on the classification performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。