<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bui-etal-2022-detect">
    <titleInfo>
        <title>Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nghi</namePart>
        <namePart type="family">Bui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steven</namePart>
        <namePart type="given">C.H.</namePart>
        <namePart type="family">Hoi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">bui-etal-2022-detect</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.57</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.57</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>812</start>
            <end>823</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5
%A Bui, Nghi
%A Wang, Yue
%A Hoi, Steven C.H.
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F bui-etal-2022-detect
%X 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.
%R 10.18653/v1/2022.findings-emnlp.57
%U https://aclanthology.org/2022.findings-emnlp.57
%U https://doi.org/10.18653/v1/2022.findings-emnlp.57
%P 812-823

Markdown (Informal)

[Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5](https://aclanthology.org/2022.findings-emnlp.57) (Bui et al., Findings 2022)

• Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5 (Bui et al., Findings 2022)

ACL

• Nghi Bui, Yue Wang, and Steven C.H. Hoi. 2022. Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 812–823, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.