Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5
Nghi Bui, Yue Wang, Steven C.H. Hoi
Abstract
Automated software debugging is a crucial task for improving the productivity of software developers. Many neural-based techniques have been proven effective for debugging-related tasks such as bug localization and program repair (or bug fixing). However, these techniques often focus only on either one of them or approach them in a stage-wise manner, ignoring the mutual benefits between them. In this work, we propose a novel unified Detect-Localize-Repair framework based on a pretrained programming language model CodeT5 to seamlessly address these tasks, named CodeT5-DLR. Specifically, we propose three objectives to adapt the generic CodeT5 for debugging: a bug detection objective to determine whether a given code snippet is buggy or not, a bug localization objective to identify the buggy lines, and a program repair objective to translate the buggy code to its fixed version. We evaluate it on each of these tasks and their combined setting on two newly collected line-level debugging datasets in Java and Python. Extensive results show that our model significantly outperforms existing baselines from both NLP and software engineering domains.
BibTeX
@inproceedings{bui-etal-2022-detect,
title = "Detect-Localize-Repair: A Unified Framework for Learning to Debug with {C}ode{T}5",
author = "Bui, Nghi and
Wang, Yue and
Hoi, Steven C.H.",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.57/",
doi = "10.18653/v1/2022.findings-emnlp.57",
pages = "812--823"
}