一句话：对程序理解任务中深度模型受标签噪声影响及噪声标签学习方法进行实证研究。
深度学习模型已广泛用于程序理解任务，并在多个基准数据集上取得先进结果。然而，这类方法的有效性高度依赖数据集质量，而程序理解数据集常包含噪声样本。其中一类典型噪声是标签噪声，即某些输入对应的目标输出不正确。本文以程序理解任务为背景，对噪声标签学习展开实证研究，旨在考察标签噪声问题在这一领域中的表现及相应学习方法的适用性。摘要未给出具体实验设置、所用数据集、对比方法与量化结论，仅明确指出标签噪声是程序理解数据集中的典型噪声形式。
Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the effectiveness of these approaches depends on the quality of their datasets, and these datasets often contain noisy data samples. A typical kind of noise in program understanding datasets is label noise, which means that the target outputs for some inputs are incorrect.
@inproceedings{paperbot11251,
title = {An Empirical Study on Noisy Label Learning for Program Understanding},
author = {Wenhan Wang and Yanzhou Li and Anran Li and Jian Zhang and Wei Ma and Yang Liu},
booktitle = {ICSE},
year = {2024},
doi = {10.1145/3597503.3639217}
}